diff options
26 files changed, 9814 insertions, 909 deletions
@@ -3364,22 +3364,26 @@ dist/Net-Ping/t/410_syn_host.t Ping Net::Ping dist/Net-Ping/t/450_service.t Ping Net::Ping dist/Net-Ping/t/500_ping_icmp.t Ping Net::Ping dist/Net-Ping/t/510_ping_udp.t Ping Net::Ping -dist/Pod-Perldoc/lib/perldoc.pod Look up Perl documentation in Pod format +dist/Pod-Perldoc/corpus/no-head.pod test file for Pod-Perldoc +dist/Pod-Perldoc/corpus/perlfunc.pod test file for Pod-Perldoc +dist/Pod-Perldoc/corpus/utf8.pod test file for Pod-Perldoc +dist/Pod-Perldoc/lib/perldoc.pod Look up Perl documentation in Pod format dist/Pod-Perldoc/lib/Pod/Perldoc/BaseTo.pm utility module for perldoc dist/Pod-Perldoc/lib/Pod/Perldoc/GetOptsOO.pm options parsing for perldoc dist/Pod-Perldoc/lib/Pod/Perldoc.pm guts of the 'perldoc' utility +dist/Pod-Perldoc/lib/Pod/Perldoc/ToANSI.pm convert POD to ANSI text dist/Pod-Perldoc/lib/Pod/Perldoc/ToChecker.pm let perldoc check POD for errors dist/Pod-Perldoc/lib/Pod/Perldoc/ToMan.pm render POD as man pages dist/Pod-Perldoc/lib/Pod/Perldoc/ToNroff.pm convert POD to nroff dist/Pod-Perldoc/lib/Pod/Perldoc/ToPod.pm convert POD to POD dist/Pod-Perldoc/lib/Pod/Perldoc/ToRtf.pm convert POD to RTF +dist/Pod-Perldoc/lib/Pod/Perldoc/ToTerm.pm convert POD to terminal output dist/Pod-Perldoc/lib/Pod/Perldoc/ToText.pm convert POD to plain text dist/Pod-Perldoc/lib/Pod/Perldoc/ToTk.pm convert POD via Tk::Pod dist/Pod-Perldoc/lib/Pod/Perldoc/ToXml.pm convert POD to XML -dist/Pod-Perldoc/t/01_about_verbose.t test Pod::Perldoc -dist/Pod-Perldoc/t/checkerbasic.t test Pod::Perldoc::ToChecker -dist/Pod-Perldoc/t/perldocbasic.t test Pod::Perldoc basic operation -dist/Pod-Perldoc/t/textbasic.t test Pod::Perldoc::ToText +dist/Pod-Perldoc/t/load.t test file for Pod-Perldoc +dist/Pod-Perldoc/t/man/_get_columns.t test file for Pod-Perldoc +dist/Pod-Perldoc/t/pod.t test file for Pod-Perldoc dist/Safe/Changes Changes for Safe.pm dist/Safe/Makefile.PL Makefile.PL for Safe.pm dist/Safe/MANIFEST MANIFEST for Safe.pm diff --git a/Porting/Maintainers.pl b/Porting/Maintainers.pl index 284c0f283a..1ffdc22094 100755 --- a/Porting/Maintainers.pl +++ b/Porting/Maintainers.pl @@ -1504,7 +1504,7 @@ use File::Glob qw(:case); 'Pod::Perldoc' => { 'MAINTAINER' => 'ferreira', - 'DISTRIBUTION' => 'FERREIRA/Pod-Perldoc-3.15_01.tar.gz', + 'DISTRIBUTION' => 'BDFOY/Pod-Perldoc-3.15_14.tar.gz', 'FILES' => q[dist/Pod-Perldoc], # in blead, the perldoc executable is generated by perldoc.PL diff --git a/dist/Pod-Perldoc/corpus/no-head.pod b/dist/Pod-Perldoc/corpus/no-head.pod new file mode 100644 index 0000000000..aa6381958a --- /dev/null +++ b/dist/Pod-Perldoc/corpus/no-head.pod @@ -0,0 +1,5 @@ +=pod + +This is a line of text + +=cut diff --git a/dist/Pod-Perldoc/corpus/perlfunc.pod b/dist/Pod-Perldoc/corpus/perlfunc.pod new file mode 100644 index 0000000000..604123daf8 --- /dev/null +++ b/dist/Pod-Perldoc/corpus/perlfunc.pod @@ -0,0 +1,8298 @@ +=head1 NAME +X<function> + +perlfunc - Perl builtin functions + +=head1 DESCRIPTION + +The functions in this section can serve as terms in an expression. +They fall into two major categories: list operators and named unary +operators. These differ in their precedence relationship with a +following comma. (See the precedence table in L<perlop>.) List +operators take more than one argument, while unary operators can never +take more than one argument. Thus, a comma terminates the argument of +a unary operator, but merely separates the arguments of a list +operator. A unary operator generally provides scalar context to its +argument, while a list operator may provide either scalar or list +contexts for its arguments. If it does both, scalar arguments +come first and list argument follow, and there can only ever +be one such list argument. For instance, splice() has three scalar +arguments followed by a list, whereas gethostbyname() has four scalar +arguments. + +In the syntax descriptions that follow, list operators that expect a +list (and provide list context for elements of the list) are shown +with LIST as an argument. Such a list may consist of any combination +of scalar arguments or list values; the list values will be included +in the list as if each individual element were interpolated at that +point in the list, forming a longer single-dimensional list value. +Commas should separate literal elements of the LIST. + +Any function in the list below may be used either with or without +parentheses around its arguments. (The syntax descriptions omit the +parentheses.) If you use parentheses, the simple but occasionally +surprising rule is this: It I<looks> like a function, therefore it I<is> a +function, and precedence doesn't matter. Otherwise it's a list +operator or unary operator, and precedence does matter. Whitespace +between the function and left parenthesis doesn't count, so sometimes +you need to be careful: + + print 1+2+4; # Prints 7. + print(1+2) + 4; # Prints 3. + print (1+2)+4; # Also prints 3! + print +(1+2)+4; # Prints 7. + print ((1+2)+4); # Prints 7. + +If you run Perl with the B<-w> switch it can warn you about this. For +example, the third line above produces: + + print (...) interpreted as function at - line 1. + Useless use of integer addition in void context at - line 1. + +A few functions take no arguments at all, and therefore work as neither +unary nor list operators. These include such functions as C<time> +and C<endpwent>. For example, C<time+86_400> always means +C<time() + 86_400>. + +For functions that can be used in either a scalar or list context, +nonabortive failure is generally indicated in scalar context by +returning the undefined value, and in list context by returning the +empty list. + +Remember the following important rule: There is B<no rule> that relates +the behavior of an expression in list context to its behavior in scalar +context, or vice versa. It might do two totally different things. +Each operator and function decides which sort of value would be most +appropriate to return in scalar context. Some operators return the +length of the list that would have been returned in list context. Some +operators return the first value in the list. Some operators return the +last value in the list. Some operators return a count of successful +operations. In general, they do what you want, unless you want +consistency. +X<context> + +A named array in scalar context is quite different from what would at +first glance appear to be a list in scalar context. You can't get a list +like C<(1,2,3)> into being in scalar context, because the compiler knows +the context at compile time. It would generate the scalar comma operator +there, not the list construction version of the comma. That means it +was never a list to start with. + +In general, functions in Perl that serve as wrappers for system calls ("syscalls") +of the same name (like chown(2), fork(2), closedir(2), etc.) return +true when they succeed and C<undef> otherwise, as is usually mentioned +in the descriptions below. This is different from the C interfaces, +which return C<-1> on failure. Exceptions to this rule include C<wait>, +C<waitpid>, and C<syscall>. System calls also set the special C<$!> +variable on failure. Other functions do not, except accidentally. + +Extension modules can also hook into the Perl parser to define new +kinds of keyword-headed expression. These may look like functions, but +may also look completely different. The syntax following the keyword +is defined entirely by the extension. If you are an implementor, see +L<perlapi/PL_keyword_plugin> for the mechanism. If you are using such +a module, see the module's documentation for details of the syntax that +it defines. + +=head2 Perl Functions by Category +X<function> + +Here are Perl's functions (including things that look like +functions, like some keywords and named operators) +arranged by category. Some functions appear in more +than one place. + +=over 4 + +=item Functions for SCALARs or strings +X<scalar> X<string> X<character> + +C<chomp>, C<chop>, C<chr>, C<crypt>, C<hex>, C<index>, C<lc>, C<lcfirst>, +C<length>, C<oct>, C<ord>, C<pack>, C<q//>, C<qq//>, C<reverse>, +C<rindex>, C<sprintf>, C<substr>, C<tr///>, C<uc>, C<ucfirst>, C<y///> + +=item Regular expressions and pattern matching +X<regular expression> X<regex> X<regexp> + +C<m//>, C<pos>, C<quotemeta>, C<s///>, C<split>, C<study>, C<qr//> + +=item Numeric functions +X<numeric> X<number> X<trigonometric> X<trigonometry> + +C<abs>, C<atan2>, C<cos>, C<exp>, C<hex>, C<int>, C<log>, C<oct>, C<rand>, +C<sin>, C<sqrt>, C<srand> + +=item Functions for real @ARRAYs +X<array> + +C<each>, C<keys>, C<pop>, C<push>, C<shift>, C<splice>, C<unshift>, C<values> + +=item Functions for list data +X<list> + +C<grep>, C<join>, C<map>, C<qw//>, C<reverse>, C<sort>, C<unpack> + +=item Functions for real %HASHes +X<hash> + +C<delete>, C<each>, C<exists>, C<keys>, C<values> + +=item Input and output functions +X<I/O> X<input> X<output> X<dbm> + +C<binmode>, C<close>, C<closedir>, C<dbmclose>, C<dbmopen>, C<die>, C<eof>, +C<fileno>, C<flock>, C<format>, C<getc>, C<print>, C<printf>, C<read>, +C<readdir>, C<rewinddir>, C<say>, C<seek>, C<seekdir>, C<select>, C<syscall>, +C<sysread>, C<sysseek>, C<syswrite>, C<tell>, C<telldir>, C<truncate>, +C<warn>, C<write> + +=item Functions for fixed-length data or records + +C<pack>, C<read>, C<syscall>, C<sysread>, C<syswrite>, C<unpack>, C<vec> + +=item Functions for filehandles, files, or directories +X<file> X<filehandle> X<directory> X<pipe> X<link> X<symlink> + +C<-I<X>>, C<chdir>, C<chmod>, C<chown>, C<chroot>, C<fcntl>, C<glob>, +C<ioctl>, C<link>, C<lstat>, C<mkdir>, C<open>, C<opendir>, +C<readlink>, C<rename>, C<rmdir>, C<stat>, C<symlink>, C<sysopen>, +C<umask>, C<unlink>, C<utime> + +=item Keywords related to the control flow of your Perl program +X<control flow> + +C<caller>, C<continue>, C<die>, C<do>, +C<dump>, C<eval>, C<evalbytes> C<exit>, +C<__FILE__>, C<goto>, C<last>, C<__LINE__>, C<next>, C<__PACKAGE__>, +C<redo>, C<return>, C<sub>, C<__SUB__>, C<wantarray> + +C<__SUB__> is only available with a C<use v5.16> (or higher) declaration or +with the C<"current_sub"> feature (see L<feature>). + +=item Keywords related to the switch feature + +C<break>, C<continue>, C<default>, C<given>, C<when> + +Except for C<continue>, these are available only if you enable the +C<"switch"> feature or use the C<CORE::> prefix. +See L<feature> and L<perlsyn/"Switch statements">. +Alternately, include a C<use v5.10> or later to the current scope. In Perl +5.14 and earlier, C<continue> required the C<"switch"> feature, like the +other keywords. + +=item Keywords related to scoping + +C<caller>, C<import>, C<local>, C<my>, C<our>, C<package>, C<state>, C<use> + +C<state> is available only if the C<"state"> feature +is enabled or if it is prefixed with C<CORE::>. See +L<feature>. Alternately, include a C<use v5.10> or later to the current scope. + +=item Miscellaneous functions + +C<defined>, C<dump>, C<eval>, C<evalbytes>, +C<formline>, C<local>, C<my>, C<our>, +C<reset>, C<scalar>, C<state>, C<undef>, C<wantarray> + +=item Functions for processes and process groups +X<process> X<pid> X<process id> + +C<alarm>, C<exec>, C<fork>, C<getpgrp>, C<getppid>, C<getpriority>, C<kill>, +C<pipe>, C<qx//>, C<readpipe>, C<setpgrp>, +C<setpriority>, C<sleep>, C<system>, +C<times>, C<wait>, C<waitpid> + +=item Keywords related to Perl modules +X<module> + +C<do>, C<import>, C<no>, C<package>, C<require>, C<use> + +=item Keywords related to classes and object-orientation +X<object> X<class> X<package> + +C<bless>, C<dbmclose>, C<dbmopen>, C<package>, C<ref>, C<tie>, C<tied>, +C<untie>, C<use> + +=item Low-level socket functions +X<socket> X<sock> + +C<accept>, C<bind>, C<connect>, C<getpeername>, C<getsockname>, +C<getsockopt>, C<listen>, C<recv>, C<send>, C<setsockopt>, C<shutdown>, +C<socket>, C<socketpair> + +=item System V interprocess communication functions +X<IPC> X<System V> X<semaphore> X<shared memory> X<memory> X<message> + +C<msgctl>, C<msgget>, C<msgrcv>, C<msgsnd>, C<semctl>, C<semget>, C<semop>, +C<shmctl>, C<shmget>, C<shmread>, C<shmwrite> + +=item Fetching user and group info +X<user> X<group> X<password> X<uid> X<gid> X<passwd> X</etc/passwd> + +C<endgrent>, C<endhostent>, C<endnetent>, C<endpwent>, C<getgrent>, +C<getgrgid>, C<getgrnam>, C<getlogin>, C<getpwent>, C<getpwnam>, +C<getpwuid>, C<setgrent>, C<setpwent> + +=item Fetching network info +X<network> X<protocol> X<host> X<hostname> X<IP> X<address> X<service> + +C<endprotoent>, C<endservent>, C<gethostbyaddr>, C<gethostbyname>, +C<gethostent>, C<getnetbyaddr>, C<getnetbyname>, C<getnetent>, +C<getprotobyname>, C<getprotobynumber>, C<getprotoent>, +C<getservbyname>, C<getservbyport>, C<getservent>, C<sethostent>, +C<setnetent>, C<setprotoent>, C<setservent> + +=item Time-related functions +X<time> X<date> + +C<gmtime>, C<localtime>, C<time>, C<times> + +=item Functions new in perl5 +X<perl5> + +C<abs>, C<bless>, C<break>, C<chomp>, C<chr>, C<continue>, C<default>, +C<exists>, C<formline>, C<given>, C<glob>, C<import>, C<lc>, C<lcfirst>, +C<lock>, C<map>, C<my>, C<no>, C<our>, C<prototype>, C<qr//>, C<qw//>, C<qx//>, +C<readline>, C<readpipe>, C<ref>, C<sub>*, C<sysopen>, C<tie>, C<tied>, C<uc>, +C<ucfirst>, C<untie>, C<use>, C<when> + +* C<sub> was a keyword in Perl 4, but in Perl 5 it is an +operator, which can be used in expressions. + +=item Functions obsoleted in perl5 + +C<dbmclose>, C<dbmopen> + +=back + +=head2 Portability +X<portability> X<Unix> X<portable> + +Perl was born in Unix and can therefore access all common Unix +system calls. In non-Unix environments, the functionality of some +Unix system calls may not be available or details of the available +functionality may differ slightly. The Perl functions affected +by this are: + +C<-X>, C<binmode>, C<chmod>, C<chown>, C<chroot>, C<crypt>, +C<dbmclose>, C<dbmopen>, C<dump>, C<endgrent>, C<endhostent>, +C<endnetent>, C<endprotoent>, C<endpwent>, C<endservent>, C<exec>, +C<fcntl>, C<flock>, C<fork>, C<getgrent>, C<getgrgid>, C<gethostbyname>, +C<gethostent>, C<getlogin>, C<getnetbyaddr>, C<getnetbyname>, C<getnetent>, +C<getppid>, C<getpgrp>, C<getpriority>, C<getprotobynumber>, +C<getprotoent>, C<getpwent>, C<getpwnam>, C<getpwuid>, +C<getservbyport>, C<getservent>, C<getsockopt>, C<glob>, C<ioctl>, +C<kill>, C<link>, C<lstat>, C<msgctl>, C<msgget>, C<msgrcv>, +C<msgsnd>, C<open>, C<pipe>, C<readlink>, C<rename>, C<select>, C<semctl>, +C<semget>, C<semop>, C<setgrent>, C<sethostent>, C<setnetent>, +C<setpgrp>, C<setpriority>, C<setprotoent>, C<setpwent>, +C<setservent>, C<setsockopt>, C<shmctl>, C<shmget>, C<shmread>, +C<shmwrite>, C<socket>, C<socketpair>, +C<stat>, C<symlink>, C<syscall>, C<sysopen>, C<system>, +C<times>, C<truncate>, C<umask>, C<unlink>, +C<utime>, C<wait>, C<waitpid> + +For more information about the portability of these functions, see +L<perlport> and other available platform-specific documentation. + +=head2 Alphabetical Listing of Perl Functions + +=over + +=item -X FILEHANDLE +X<-r>X<-w>X<-x>X<-o>X<-R>X<-W>X<-X>X<-O>X<-e>X<-z>X<-s>X<-f>X<-d>X<-l>X<-p> +X<-S>X<-b>X<-c>X<-t>X<-u>X<-g>X<-k>X<-T>X<-B>X<-M>X<-A>X<-C> + +=item -X EXPR + +=item -X DIRHANDLE + +=item -X + +A file test, where X is one of the letters listed below. This unary +operator takes one argument, either a filename, a filehandle, or a dirhandle, +and tests the associated file to see if something is true about it. If the +argument is omitted, tests C<$_>, except for C<-t>, which tests STDIN. +Unless otherwise documented, it returns C<1> for true and C<''> for false, or +the undefined value if the file doesn't exist. Despite the funny +names, precedence is the same as any other named unary operator. The +operator may be any of: + + -r File is readable by effective uid/gid. + -w File is writable by effective uid/gid. + -x File is executable by effective uid/gid. + -o File is owned by effective uid. + + -R File is readable by real uid/gid. + -W File is writable by real uid/gid. + -X File is executable by real uid/gid. + -O File is owned by real uid. + + -e File exists. + -z File has zero size (is empty). + -s File has nonzero size (returns size in bytes). + + -f File is a plain file. + -d File is a directory. + -l File is a symbolic link. + -p File is a named pipe (FIFO), or Filehandle is a pipe. + -S File is a socket. + -b File is a block special file. + -c File is a character special file. + -t Filehandle is opened to a tty. + + -u File has setuid bit set. + -g File has setgid bit set. + -k File has sticky bit set. + + -T File is an ASCII text file (heuristic guess). + -B File is a "binary" file (opposite of -T). + + -M Script start time minus file modification time, in days. + -A Same for access time. + -C Same for inode change time (Unix, may differ for other platforms) + +Example: + + while (<>) { + chomp; + next unless -f $_; # ignore specials + #... + } + +Note that C<-s/a/b/> does not do a negated substitution. Saying +C<-exp($foo)> still works as expected, however: only single letters +following a minus are interpreted as file tests. + +These operators are exempt from the "looks like a function rule" described +above. That is, an opening parenthesis after the operator does not affect +how much of the following code constitutes the argument. Put the opening +parentheses before the operator to separate it from code that follows (this +applies only to operators with higher precedence than unary operators, of +course): + + -s($file) + 1024 # probably wrong; same as -s($file + 1024) + (-s $file) + 1024 # correct + +The interpretation of the file permission operators C<-r>, C<-R>, +C<-w>, C<-W>, C<-x>, and C<-X> is by default based solely on the mode +of the file and the uids and gids of the user. There may be other +reasons you can't actually read, write, or execute the file: for +example network filesystem access controls, ACLs (access control lists), +read-only filesystems, and unrecognized executable formats. Note +that the use of these six specific operators to verify if some operation +is possible is usually a mistake, because it may be open to race +conditions. + +Also note that, for the superuser on the local filesystems, the C<-r>, +C<-R>, C<-w>, and C<-W> tests always return 1, and C<-x> and C<-X> return 1 +if any execute bit is set in the mode. Scripts run by the superuser +may thus need to do a stat() to determine the actual mode of the file, +or temporarily set their effective uid to something else. + +If you are using ACLs, there is a pragma called C<filetest> that may +produce more accurate results than the bare stat() mode bits. +When under C<use filetest 'access'> the above-mentioned filetests +test whether the permission can(not) be granted using the +access(2) family of system calls. Also note that the C<-x> and C<-X> may +under this pragma return true even if there are no execute permission +bits set (nor any extra execute permission ACLs). This strangeness is +due to the underlying system calls' definitions. Note also that, due to +the implementation of C<use filetest 'access'>, the C<_> special +filehandle won't cache the results of the file tests when this pragma is +in effect. Read the documentation for the C<filetest> pragma for more +information. + +The C<-T> and C<-B> switches work as follows. The first block or so of the +file is examined for odd characters such as strange control codes or +characters with the high bit set. If too many strange characters (>30%) +are found, it's a C<-B> file; otherwise it's a C<-T> file. Also, any file +containing a zero byte in the first block is considered a binary file. If C<-T> +or C<-B> is used on a filehandle, the current IO buffer is examined +rather than the first block. Both C<-T> and C<-B> return true on an empty +file, or a file at EOF when testing a filehandle. Because you have to +read a file to do the C<-T> test, on most occasions you want to use a C<-f> +against the file first, as in C<next unless -f $file && -T $file>. + +If any of the file tests (or either the C<stat> or C<lstat> operator) is given +the special filehandle consisting of a solitary underline, then the stat +structure of the previous file test (or stat operator) is used, saving +a system call. (This doesn't work with C<-t>, and you need to remember +that lstat() and C<-l> leave values in the stat structure for the +symbolic link, not the real file.) (Also, if the stat buffer was filled by +an C<lstat> call, C<-T> and C<-B> will reset it with the results of C<stat _>). +Example: + + print "Can do.\n" if -r $a || -w _ || -x _; + + stat($filename); + print "Readable\n" if -r _; + print "Writable\n" if -w _; + print "Executable\n" if -x _; + print "Setuid\n" if -u _; + print "Setgid\n" if -g _; + print "Sticky\n" if -k _; + print "Text\n" if -T _; + print "Binary\n" if -B _; + +As of Perl 5.9.1, as a form of purely syntactic sugar, you can stack file +test operators, in a way that C<-f -w -x $file> is equivalent to +C<-x $file && -w _ && -f _>. (This is only fancy fancy: if you use +the return value of C<-f $file> as an argument to another filetest +operator, no special magic will happen.) + +Portability issues: L<perlport/-X>. + +=item abs VALUE +X<abs> X<absolute> + +=item abs + +Returns the absolute value of its argument. +If VALUE is omitted, uses C<$_>. + +=item accept NEWSOCKET,GENERICSOCKET +X<accept> + +Accepts an incoming socket connect, just as accept(2) +does. Returns the packed address if it succeeded, false otherwise. +See the example in L<perlipc/"Sockets: Client/Server Communication">. + +On systems that support a close-on-exec flag on files, the flag will +be set for the newly opened file descriptor, as determined by the +value of $^F. See L<perlvar/$^F>. + +=item alarm SECONDS +X<alarm> +X<SIGALRM> +X<timer> + +=item alarm + +Arranges to have a SIGALRM delivered to this process after the +specified number of wallclock seconds has elapsed. If SECONDS is not +specified, the value stored in C<$_> is used. (On some machines, +unfortunately, the elapsed time may be up to one second less or more +than you specified because of how seconds are counted, and process +scheduling may delay the delivery of the signal even further.) + +Only one timer may be counting at once. Each call disables the +previous timer, and an argument of C<0> may be supplied to cancel the +previous timer without starting a new one. The returned value is the +amount of time remaining on the previous timer. + +For delays of finer granularity than one second, the Time::HiRes module +(from CPAN, and starting from Perl 5.8 part of the standard +distribution) provides ualarm(). You may also use Perl's four-argument +version of select() leaving the first three arguments undefined, or you +might be able to use the C<syscall> interface to access setitimer(2) if +your system supports it. See L<perlfaq8> for details. + +It is usually a mistake to intermix C<alarm> and C<sleep> calls, because +C<sleep> may be internally implemented on your system with C<alarm>. + +If you want to use C<alarm> to time out a system call you need to use an +C<eval>/C<die> pair. You can't rely on the alarm causing the system call to +fail with C<$!> set to C<EINTR> because Perl sets up signal handlers to +restart system calls on some systems. Using C<eval>/C<die> always works, +modulo the caveats given in L<perlipc/"Signals">. + + eval { + local $SIG{ALRM} = sub { die "alarm\n" }; # NB: \n required + alarm $timeout; + $nread = sysread SOCKET, $buffer, $size; + alarm 0; + }; + if ($@) { + die unless $@ eq "alarm\n"; # propagate unexpected errors + # timed out + } + else { + # didn't + } + +For more information see L<perlipc>. + +Portability issues: L<perlport/alarm>. + +=item atan2 Y,X +X<atan2> X<arctangent> X<tan> X<tangent> + +Returns the arctangent of Y/X in the range -PI to PI. + +For the tangent operation, you may use the C<Math::Trig::tan> +function, or use the familiar relation: + + sub tan { sin($_[0]) / cos($_[0]) } + +The return value for C<atan2(0,0)> is implementation-defined; consult +your atan2(3) manpage for more information. + +Portability issues: L<perlport/atan2>. + +=item bind SOCKET,NAME +X<bind> + +Binds a network address to a socket, just as bind(2) +does. Returns true if it succeeded, false otherwise. NAME should be a +packed address of the appropriate type for the socket. See the examples in +L<perlipc/"Sockets: Client/Server Communication">. + +=item binmode FILEHANDLE, LAYER +X<binmode> X<binary> X<text> X<DOS> X<Windows> + +=item binmode FILEHANDLE + +Arranges for FILEHANDLE to be read or written in "binary" or "text" +mode on systems where the run-time libraries distinguish between +binary and text files. If FILEHANDLE is an expression, the value is +taken as the name of the filehandle. Returns true on success, +otherwise it returns C<undef> and sets C<$!> (errno). + +On some systems (in general, DOS- and Windows-based systems) binmode() +is necessary when you're not working with a text file. For the sake +of portability it is a good idea always to use it when appropriate, +and never to use it when it isn't appropriate. Also, people can +set their I/O to be by default UTF8-encoded Unicode, not bytes. + +In other words: regardless of platform, use binmode() on binary data, +like images, for example. + +If LAYER is present it is a single string, but may contain multiple +directives. The directives alter the behaviour of the filehandle. +When LAYER is present, using binmode on a text file makes sense. + +If LAYER is omitted or specified as C<:raw> the filehandle is made +suitable for passing binary data. This includes turning off possible CRLF +translation and marking it as bytes (as opposed to Unicode characters). +Note that, despite what may be implied in I<"Programming Perl"> (the +Camel, 3rd edition) or elsewhere, C<:raw> is I<not> simply the inverse of C<:crlf>. +Other layers that would affect the binary nature of the stream are +I<also> disabled. See L<PerlIO>, L<perlrun>, and the discussion about the +PERLIO environment variable. + +The C<:bytes>, C<:crlf>, C<:utf8>, and any other directives of the +form C<:...>, are called I/O I<layers>. The C<open> pragma can be used to +establish default I/O layers. See L<open>. + +I<The LAYER parameter of the binmode() function is described as "DISCIPLINE" +in "Programming Perl, 3rd Edition". However, since the publishing of this +book, by many known as "Camel III", the consensus of the naming of this +functionality has moved from "discipline" to "layer". All documentation +of this version of Perl therefore refers to "layers" rather than to +"disciplines". Now back to the regularly scheduled documentation...> + +To mark FILEHANDLE as UTF-8, use C<:utf8> or C<:encoding(UTF-8)>. +C<:utf8> just marks the data as UTF-8 without further checking, +while C<:encoding(UTF-8)> checks the data for actually being valid +UTF-8. More details can be found in L<PerlIO::encoding>. + +In general, binmode() should be called after open() but before any I/O +is done on the filehandle. Calling binmode() normally flushes any +pending buffered output data (and perhaps pending input data) on the +handle. An exception to this is the C<:encoding> layer that +changes the default character encoding of the handle; see L</open>. +The C<:encoding> layer sometimes needs to be called in +mid-stream, and it doesn't flush the stream. The C<:encoding> +also implicitly pushes on top of itself the C<:utf8> layer because +internally Perl operates on UTF8-encoded Unicode characters. + +The operating system, device drivers, C libraries, and Perl run-time +system all conspire to let the programmer treat a single +character (C<\n>) as the line terminator, irrespective of external +representation. On many operating systems, the native text file +representation matches the internal representation, but on some +platforms the external representation of C<\n> is made up of more than +one character. + +All variants of Unix, Mac OS (old and new), and Stream_LF files on VMS use +a single character to end each line in the external representation of text +(even though that single character is CARRIAGE RETURN on old, pre-Darwin +flavors of Mac OS, and is LINE FEED on Unix and most VMS files). In other +systems like OS/2, DOS, and the various flavors of MS-Windows, your program +sees a C<\n> as a simple C<\cJ>, but what's stored in text files are the +two characters C<\cM\cJ>. That means that if you don't use binmode() on +these systems, C<\cM\cJ> sequences on disk will be converted to C<\n> on +input, and any C<\n> in your program will be converted back to C<\cM\cJ> on +output. This is what you want for text files, but it can be disastrous for +binary files. + +Another consequence of using binmode() (on some systems) is that +special end-of-file markers will be seen as part of the data stream. +For systems from the Microsoft family this means that, if your binary +data contain C<\cZ>, the I/O subsystem will regard it as the end of +the file, unless you use binmode(). + +binmode() is important not only for readline() and print() operations, +but also when using read(), seek(), sysread(), syswrite() and tell() +(see L<perlport> for more details). See the C<$/> and C<$\> variables +in L<perlvar> for how to manually set your input and output +line-termination sequences. + +Portability issues: L<perlport/binmode>. + +=item bless REF,CLASSNAME +X<bless> + +=item bless REF + +This function tells the thingy referenced by REF that it is now an object +in the CLASSNAME package. If CLASSNAME is omitted, the current package +is used. Because a C<bless> is often the last thing in a constructor, +it returns the reference for convenience. Always use the two-argument +version if a derived class might inherit the function doing the blessing. +SeeL<perlobj> for more about the blessing (and blessings) of objects. + +Consider always blessing objects in CLASSNAMEs that are mixed case. +Namespaces with all lowercase names are considered reserved for +Perl pragmata. Builtin types have all uppercase names. To prevent +confusion, you may wish to avoid such package names as well. Make sure +that CLASSNAME is a true value. + +See L<perlmod/"Perl Modules">. + +=item break + +Break out of a C<given()> block. + +This keyword is enabled by the C<"switch"> feature: see +L<feature> for more information. You can also access it by +prefixing it with C<CORE::>. Alternately, include a C<use +v5.10> or later to the current scope. + +=item caller EXPR +X<caller> X<call stack> X<stack> X<stack trace> + +=item caller + +Returns the context of the current subroutine call. In scalar context, +returns the caller's package name if there I<is> a caller (that is, if +we're in a subroutine or C<eval> or C<require>) and the undefined value +otherwise. In list context, returns + + # 0 1 2 + ($package, $filename, $line) = caller; + +With EXPR, it returns some extra information that the debugger uses to +print a stack trace. The value of EXPR indicates how many call frames +to go back before the current one. + + # 0 1 2 3 4 + ($package, $filename, $line, $subroutine, $hasargs, + + # 5 6 7 8 9 10 + $wantarray, $evaltext, $is_require, $hints, $bitmask, $hinthash) + = caller($i); + +Here $subroutine may be C<(eval)> if the frame is not a subroutine +call, but an C<eval>. In such a case additional elements $evaltext and +C<$is_require> are set: C<$is_require> is true if the frame is created by a +C<require> or C<use> statement, $evaltext contains the text of the +C<eval EXPR> statement. In particular, for an C<eval BLOCK> statement, +$subroutine is C<(eval)>, but $evaltext is undefined. (Note also that +each C<use> statement creates a C<require> frame inside an C<eval EXPR> +frame.) $subroutine may also be C<(unknown)> if this particular +subroutine happens to have been deleted from the symbol table. +C<$hasargs> is true if a new instance of C<@_> was set up for the frame. +C<$hints> and C<$bitmask> contain pragmatic hints that the caller was +compiled with. The C<$hints> and C<$bitmask> values are subject to change +between versions of Perl, and are not meant for external use. + +C<$hinthash> is a reference to a hash containing the value of C<%^H> when the +caller was compiled, or C<undef> if C<%^H> was empty. Do not modify the values +of this hash, as they are the actual values stored in the optree. + +Furthermore, when called from within the DB package, caller returns more +detailed information: it sets the list variable C<@DB::args> to be the +arguments with which the subroutine was invoked. + +Be aware that the optimizer might have optimized call frames away before +C<caller> had a chance to get the information. That means that C<caller(N)> +might not return information about the call frame you expect it to, for +C<< N > 1 >>. In particular, C<@DB::args> might have information from the +previous time C<caller> was called. + +Be aware that setting C<@DB::args> is I<best effort>, intended for +debugging or generating backtraces, and should not be relied upon. In +particular, as C<@_> contains aliases to the caller's arguments, Perl does +not take a copy of C<@_>, so C<@DB::args> will contain modifications the +subroutine makes to C<@_> or its contents, not the original values at call +time. C<@DB::args>, like C<@_>, does not hold explicit references to its +elements, so under certain cases its elements may have become freed and +reallocated for other variables or temporary values. Finally, a side effect +of the current implementation is that the effects of C<shift @_> can +I<normally> be undone (but not C<pop @_> or other splicing, I<and> not if a +reference to C<@_> has been taken, I<and> subject to the caveat about reallocated +elements), so C<@DB::args> is actually a hybrid of the current state and +initial state of C<@_>. Buyer beware. + +=item chdir EXPR +X<chdir> +X<cd> +X<directory, change> + +=item chdir FILEHANDLE + +=item chdir DIRHANDLE + +=item chdir + +Changes the working directory to EXPR, if possible. If EXPR is omitted, +changes to the directory specified by C<$ENV{HOME}>, if set; if not, +changes to the directory specified by C<$ENV{LOGDIR}>. (Under VMS, the +variable C<$ENV{SYS$LOGIN}> is also checked, and used if it is set.) If +neither is set, C<chdir> does nothing. It returns true on success, +false otherwise. See the example under C<die>. + +On systems that support fchdir(2), you may pass a filehandle or +directory handle as the argument. On systems that don't support fchdir(2), +passing handles raises an exception. + +=item chmod LIST +X<chmod> X<permission> X<mode> + +Changes the permissions of a list of files. The first element of the +list must be the numeric mode, which should probably be an octal +number, and which definitely should I<not> be a string of octal digits: +C<0644> is okay, but C<"0644"> is not. Returns the number of files +successfully changed. See also L</oct> if all you have is a string. + + $cnt = chmod 0755, "foo", "bar"; + chmod 0755, @executables; + $mode = "0644"; chmod $mode, "foo"; # !!! sets mode to + # --w----r-T + $mode = "0644"; chmod oct($mode), "foo"; # this is better + $mode = 0644; chmod $mode, "foo"; # this is best + +On systems that support fchmod(2), you may pass filehandles among the +files. On systems that don't support fchmod(2), passing filehandles raises +an exception. Filehandles must be passed as globs or glob references to be +recognized; barewords are considered filenames. + + open(my $fh, "<", "foo"); + my $perm = (stat $fh)[2] & 07777; + chmod($perm | 0600, $fh); + +You can also import the symbolic C<S_I*> constants from the C<Fcntl> +module: + + use Fcntl qw( :mode ); + chmod S_IRWXU|S_IRGRP|S_IXGRP|S_IROTH|S_IXOTH, @executables; + # Identical to the chmod 0755 of the example above. + +Portability issues: L<perlport/chmod>. + +=item chomp VARIABLE +X<chomp> X<INPUT_RECORD_SEPARATOR> X<$/> X<newline> X<eol> + +=item chomp( LIST ) + +=item chomp + +This safer version of L</chop> removes any trailing string +that corresponds to the current value of C<$/> (also known as +$INPUT_RECORD_SEPARATOR in the C<English> module). It returns the total +number of characters removed from all its arguments. It's often used to +remove the newline from the end of an input record when you're worried +that the final record may be missing its newline. When in paragraph +mode (C<$/ = "">), it removes all trailing newlines from the string. +When in slurp mode (C<$/ = undef>) or fixed-length record mode (C<$/> is +a reference to an integer or the like; see L<perlvar>) chomp() won't +remove anything. +If VARIABLE is omitted, it chomps C<$_>. Example: + + while (<>) { + chomp; # avoid \n on last field + @array = split(/:/); + # ... + } + +If VARIABLE is a hash, it chomps the hash's values, but not its keys. + +You can actually chomp anything that's an lvalue, including an assignment: + + chomp($cwd = `pwd`); + chomp($answer = <STDIN>); + +If you chomp a list, each element is chomped, and the total number of +characters removed is returned. + +Note that parentheses are necessary when you're chomping anything +that is not a simple variable. This is because C<chomp $cwd = `pwd`;> +is interpreted as C<(chomp $cwd) = `pwd`;>, rather than as +C<chomp( $cwd = `pwd` )> which you might expect. Similarly, +C<chomp $a, $b> is interpreted as C<chomp($a), $b> rather than +as C<chomp($a, $b)>. + +=item chop VARIABLE +X<chop> + +=item chop( LIST ) + +=item chop + +Chops off the last character of a string and returns the character +chopped. It is much more efficient than C<s/.$//s> because it neither +scans nor copies the string. If VARIABLE is omitted, chops C<$_>. +If VARIABLE is a hash, it chops the hash's values, but not its keys. + +You can actually chop anything that's an lvalue, including an assignment. + +If you chop a list, each element is chopped. Only the value of the +last C<chop> is returned. + +Note that C<chop> returns the last character. To return all but the last +character, use C<substr($string, 0, -1)>. + +See also L</chomp>. + +=item chown LIST +X<chown> X<owner> X<user> X<group> + +Changes the owner (and group) of a list of files. The first two +elements of the list must be the I<numeric> uid and gid, in that +order. A value of -1 in either position is interpreted by most +systems to leave that value unchanged. Returns the number of files +successfully changed. + + $cnt = chown $uid, $gid, 'foo', 'bar'; + chown $uid, $gid, @filenames; + +On systems that support fchown(2), you may pass filehandles among the +files. On systems that don't support fchown(2), passing filehandles raises +an exception. Filehandles must be passed as globs or glob references to be +recognized; barewords are considered filenames. + +Here's an example that looks up nonnumeric uids in the passwd file: + + print "User: "; + chomp($user = <STDIN>); + print "Files: "; + chomp($pattern = <STDIN>); + + ($login,$pass,$uid,$gid) = getpwnam($user) + or die "$user not in passwd file"; + + @ary = glob($pattern); # expand filenames + chown $uid, $gid, @ary; + +On most systems, you are not allowed to change the ownership of the +file unless you're the superuser, although you should be able to change +the group to any of your secondary groups. On insecure systems, these +restrictions may be relaxed, but this is not a portable assumption. +On POSIX systems, you can detect this condition this way: + + use POSIX qw(sysconf _PC_CHOWN_RESTRICTED); + $can_chown_giveaway = not sysconf(_PC_CHOWN_RESTRICTED); + +Portability issues: L<perlport/chmod>. + +=item chr NUMBER +X<chr> X<character> X<ASCII> X<Unicode> + +=item chr + +Returns the character represented by that NUMBER in the character set. +For example, C<chr(65)> is C<"A"> in either ASCII or Unicode, and +chr(0x263a) is a Unicode smiley face. + +Negative values give the Unicode replacement character (chr(0xfffd)), +except under the L<bytes> pragma, where the low eight bits of the value +(truncated to an integer) are used. + +If NUMBER is omitted, uses C<$_>. + +For the reverse, use L</ord>. + +Note that characters from 128 to 255 (inclusive) are by default +internally not encoded as UTF-8 for backward compatibility reasons. + +See L<perlunicode> for more about Unicode. + +=item chroot FILENAME +X<chroot> X<root> + +=item chroot + +This function works like the system call by the same name: it makes the +named directory the new root directory for all further pathnames that +begin with a C</> by your process and all its children. (It doesn't +change your current working directory, which is unaffected.) For security +reasons, this call is restricted to the superuser. If FILENAME is +omitted, does a C<chroot> to C<$_>. + +Portability issues: L<perlport/chroot>. + +=item close FILEHANDLE +X<close> + +=item close + +Closes the file or pipe associated with the filehandle, flushes the IO +buffers, and closes the system file descriptor. Returns true if those +operations succeed and if no error was reported by any PerlIO +layer. Closes the currently selected filehandle if the argument is +omitted. + +You don't have to close FILEHANDLE if you are immediately going to do +another C<open> on it, because C<open> closes it for you. (See +L<open|/open FILEHANDLE>.) However, an explicit C<close> on an input file resets the line +counter (C<$.>), while the implicit close done by C<open> does not. + +If the filehandle came from a piped open, C<close> returns false if one of +the other syscalls involved fails or if its program exits with non-zero +status. If the only problem was that the program exited non-zero, C<$!> +will be set to C<0>. Closing a pipe also waits for the process executing +on the pipe to exit--in case you wish to look at the output of the pipe +afterwards--and implicitly puts the exit status value of that command into +C<$?> and C<${^CHILD_ERROR_NATIVE}>. + +If there are multiple threads running, C<close> on a filehandle from a +piped open returns true without waiting for the child process to terminate, +if the filehandle is still open in another thread. + +Closing the read end of a pipe before the process writing to it at the +other end is done writing results in the writer receiving a SIGPIPE. If +the other end can't handle that, be sure to read all the data before +closing the pipe. + +Example: + + open(OUTPUT, '|sort >foo') # pipe to sort + or die "Can't start sort: $!"; + #... # print stuff to output + close OUTPUT # wait for sort to finish + or warn $! ? "Error closing sort pipe: $!" + : "Exit status $? from sort"; + open(INPUT, 'foo') # get sort's results + or die "Can't open 'foo' for input: $!"; + +FILEHANDLE may be an expression whose value can be used as an indirect +filehandle, usually the real filehandle name or an autovivified handle. + +=item closedir DIRHANDLE +X<closedir> + +Closes a directory opened by C<opendir> and returns the success of that +system call. + +=item connect SOCKET,NAME +X<connect> + +Attempts to connect to a remote socket, just like connect(2). +Returns true if it succeeded, false otherwise. NAME should be a +packed address of the appropriate type for the socket. See the examples in +L<perlipc/"Sockets: Client/Server Communication">. + +=item continue BLOCK +X<continue> + +=item continue + +When followed by a BLOCK, C<continue> is actually a +flow control statement rather than a function. If +there is a C<continue> BLOCK attached to a BLOCK (typically in a C<while> or +C<foreach>), it is always executed just before the conditional is about to +be evaluated again, just like the third part of a C<for> loop in C. Thus +it can be used to increment a loop variable, even when the loop has been +continued via the C<next> statement (which is similar to the C C<continue> +statement). + +C<last>, C<next>, or C<redo> may appear within a C<continue> +block; C<last> and C<redo> behave as if they had been executed within +the main block. So will C<next>, but since it will execute a C<continue> +block, it may be more entertaining. + + while (EXPR) { + ### redo always comes here + do_something; + } continue { + ### next always comes here + do_something_else; + # then back the top to re-check EXPR + } + ### last always comes here + +Omitting the C<continue> section is equivalent to using an +empty one, logically enough, so C<next> goes directly back +to check the condition at the top of the loop. + +When there is no BLOCK, C<continue> is a function that +falls through the current C<when> or C<default> block instead of iterating +a dynamically enclosing C<foreach> or exiting a lexically enclosing C<given>. +In Perl 5.14 and earlier, this form of C<continue> was +only available when the C<"switch"> feature was enabled. +See L<feature> and L<perlsyn/"Switch statements"> for more +information. + +=item cos EXPR +X<cos> X<cosine> X<acos> X<arccosine> + +=item cos + +Returns the cosine of EXPR (expressed in radians). If EXPR is omitted, +takes the cosine of C<$_>. + +For the inverse cosine operation, you may use the C<Math::Trig::acos()> +function, or use this relation: + + sub acos { atan2( sqrt(1 - $_[0] * $_[0]), $_[0] ) } + +=item crypt PLAINTEXT,SALT +X<crypt> X<digest> X<hash> X<salt> X<plaintext> X<password> +X<decrypt> X<cryptography> X<passwd> X<encrypt> + +Creates a digest string exactly like the crypt(3) function in the C +library (assuming that you actually have a version there that has not +been extirpated as a potential munition). + +crypt() is a one-way hash function. The PLAINTEXT and SALT are turned +into a short string, called a digest, which is returned. The same +PLAINTEXT and SALT will always return the same string, but there is no +(known) way to get the original PLAINTEXT from the hash. Small +changes in the PLAINTEXT or SALT will result in large changes in the +digest. + +There is no decrypt function. This function isn't all that useful for +cryptography (for that, look for F<Crypt> modules on your nearby CPAN +mirror) and the name "crypt" is a bit of a misnomer. Instead it is +primarily used to check if two pieces of text are the same without +having to transmit or store the text itself. An example is checking +if a correct password is given. The digest of the password is stored, +not the password itself. The user types in a password that is +crypt()'d with the same salt as the stored digest. If the two digests +match, the password is correct. + +When verifying an existing digest string you should use the digest as +the salt (like C<crypt($plain, $digest) eq $digest>). The SALT used +to create the digest is visible as part of the digest. This ensures +crypt() will hash the new string with the same salt as the digest. +This allows your code to work with the standard L<crypt|/crypt> and +with more exotic implementations. In other words, assume +nothing about the returned string itself nor about how many bytes +of SALT may matter. + +Traditionally the result is a string of 13 bytes: two first bytes of +the salt, followed by 11 bytes from the set C<[./0-9A-Za-z]>, and only +the first eight bytes of PLAINTEXT mattered. But alternative +hashing schemes (like MD5), higher level security schemes (like C2), +and implementations on non-Unix platforms may produce different +strings. + +When choosing a new salt create a random two character string whose +characters come from the set C<[./0-9A-Za-z]> (like C<join '', ('.', +'/', 0..9, 'A'..'Z', 'a'..'z')[rand 64, rand 64]>). This set of +characters is just a recommendation; the characters allowed in +the salt depend solely on your system's crypt library, and Perl can't +restrict what salts C<crypt()> accepts. + +Here's an example that makes sure that whoever runs this program knows +their password: + + $pwd = (getpwuid($<))[1]; + + system "stty -echo"; + print "Password: "; + chomp($word = <STDIN>); + print "\n"; + system "stty echo"; + + if (crypt($word, $pwd) ne $pwd) { + die "Sorry...\n"; + } else { + print "ok\n"; + } + +Of course, typing in your own password to whoever asks you +for it is unwise. + +The L<crypt|/crypt> function is unsuitable for hashing large quantities +of data, not least of all because you can't get the information +back. Look at the L<Digest> module for more robust algorithms. + +If using crypt() on a Unicode string (which I<potentially> has +characters with codepoints above 255), Perl tries to make sense +of the situation by trying to downgrade (a copy of) +the string back to an eight-bit byte string before calling crypt() +(on that copy). If that works, good. If not, crypt() dies with +C<Wide character in crypt>. + +Portability issues: L<perlport/crypt>. + +=item dbmclose HASH +X<dbmclose> + +[This function has been largely superseded by the C<untie> function.] + +Breaks the binding between a DBM file and a hash. + +Portability issues: L<perlport/dbmclose>. + +=item dbmopen HASH,DBNAME,MASK +X<dbmopen> X<dbm> X<ndbm> X<sdbm> X<gdbm> + +[This function has been largely superseded by the +L<tie|/tie VARIABLE,CLASSNAME,LIST> function.] + +This binds a dbm(3), ndbm(3), sdbm(3), gdbm(3), or Berkeley DB file to a +hash. HASH is the name of the hash. (Unlike normal C<open>, the first +argument is I<not> a filehandle, even though it looks like one). DBNAME +is the name of the database (without the F<.dir> or F<.pag> extension if +any). If the database does not exist, it is created with protection +specified by MASK (as modified by the C<umask>). If your system supports +only the older DBM functions, you may make only one C<dbmopen> call in your +program. In older versions of Perl, if your system had neither DBM nor +ndbm, calling C<dbmopen> produced a fatal error; it now falls back to +sdbm(3). + +If you don't have write access to the DBM file, you can only read hash +variables, not set them. If you want to test whether you can write, +either use file tests or try setting a dummy hash entry inside an C<eval> +to trap the error. + +Note that functions such as C<keys> and C<values> may return huge lists +when used on large DBM files. You may prefer to use the C<each> +function to iterate over large DBM files. Example: + + # print out history file offsets + dbmopen(%HIST,'/usr/lib/news/history',0666); + while (($key,$val) = each %HIST) { + print $key, ' = ', unpack('L',$val), "\n"; + } + dbmclose(%HIST); + +See also L<AnyDBM_File> for a more general description of the pros and +cons of the various dbm approaches, as well as L<DB_File> for a particularly +rich implementation. + +You can control which DBM library you use by loading that library +before you call dbmopen(): + + use DB_File; + dbmopen(%NS_Hist, "$ENV{HOME}/.netscape/history.db") + or die "Can't open netscape history file: $!"; + +Portability issues: L<perlport/dbmopen>. + +=item default BLOCK + +Within a C<foreach> or a C<given>, a C<default> BLOCK acts like a C<when> +that's always true. Only available after Perl 5.10, and only if the +C<switch> feature has been requested or if the keyword is prefixed with +C<CORE::>. See L</when>. + +=item defined EXPR +X<defined> X<undef> X<undefined> + +=item defined + +Returns a Boolean value telling whether EXPR has a value other than +the undefined value C<undef>. If EXPR is not present, C<$_> is +checked. + +Many operations return C<undef> to indicate failure, end of file, +system error, uninitialized variable, and other exceptional +conditions. This function allows you to distinguish C<undef> from +other values. (A simple Boolean test will not distinguish among +C<undef>, zero, the empty string, and C<"0">, which are all equally +false.) Note that since C<undef> is a valid scalar, its presence +doesn't I<necessarily> indicate an exceptional condition: C<pop> +returns C<undef> when its argument is an empty array, I<or> when the +element to return happens to be C<undef>. + +You may also use C<defined(&func)> to check whether subroutine C<&func> +has ever been defined. The return value is unaffected by any forward +declarations of C<&func>. A subroutine that is not defined +may still be callable: its package may have an C<AUTOLOAD> method that +makes it spring into existence the first time that it is called; see +L<perlsub>. + +Use of C<defined> on aggregates (hashes and arrays) is deprecated. It +used to report whether memory for that aggregate had ever been +allocated. This behavior may disappear in future versions of Perl. +You should instead use a simple test for size: + + if (@an_array) { print "has array elements\n" } + if (%a_hash) { print "has hash members\n" } + +When used on a hash element, it tells you whether the value is defined, +not whether the key exists in the hash. Use L</exists> for the latter +purpose. + +Examples: + + print if defined $switch{D}; + print "$val\n" while defined($val = pop(@ary)); + die "Can't readlink $sym: $!" + unless defined($value = readlink $sym); + sub foo { defined &$bar ? &$bar(@_) : die "No bar"; } + $debugging = 0 unless defined $debugging; + +Note: Many folks tend to overuse C<defined> and are then surprised to +discover that the number C<0> and C<""> (the zero-length string) are, in fact, +defined values. For example, if you say + + "ab" =~ /a(.*)b/; + +The pattern match succeeds and C<$1> is defined, although it +matched "nothing". It didn't really fail to match anything. Rather, it +matched something that happened to be zero characters long. This is all +very above-board and honest. When a function returns an undefined value, +it's an admission that it couldn't give you an honest answer. So you +should use C<defined> only when questioning the integrity of what +you're trying to do. At other times, a simple comparison to C<0> or C<""> is +what you want. + +See also L</undef>, L</exists>, L</ref>. + +=item delete EXPR +X<delete> + +Given an expression that specifies an element or slice of a hash, C<delete> +deletes the specified elements from that hash so that exists() on that element +no longer returns true. Setting a hash element to the undefined value does +not remove its key, but deleting it does; see L</exists>. + +In list context, returns the value or values deleted, or the last such +element in scalar context. The return list's length always matches that of +the argument list: deleting non-existent elements returns the undefined value +in their corresponding positions. + +delete() may also be used on arrays and array slices, but its behavior is less +straightforward. Although exists() will return false for deleted entries, +deleting array elements never changes indices of existing values; use shift() +or splice() for that. However, if all deleted elements fall at the end of an +array, the array's size shrinks to the position of the highest element that +still tests true for exists(), or to 0 if none do. + +B<WARNING:> Calling delete on array values is deprecated and likely to +be removed in a future version of Perl. + +Deleting from C<%ENV> modifies the environment. Deleting from a hash tied to +a DBM file deletes the entry from the DBM file. Deleting from a C<tied> hash +or array may not necessarily return anything; it depends on the implementation +of the C<tied> package's DELETE method, which may do whatever it pleases. + +The C<delete local EXPR> construct localizes the deletion to the current +block at run time. Until the block exits, elements locally deleted +temporarily no longer exist. See L<perlsub/"Localized deletion of elements +of composite types">. + + %hash = (foo => 11, bar => 22, baz => 33); + $scalar = delete $hash{foo}; # $scalar is 11 + $scalar = delete @hash{qw(foo bar)}; # $scalar is 22 + @array = delete @hash{qw(foo bar baz)}; # @array is (undef,undef,33) + +The following (inefficiently) deletes all the values of %HASH and @ARRAY: + + foreach $key (keys %HASH) { + delete $HASH{$key}; + } + + foreach $index (0 .. $#ARRAY) { + delete $ARRAY[$index]; + } + +And so do these: + + delete @HASH{keys %HASH}; + + delete @ARRAY[0 .. $#ARRAY]; + +But both are slower than assigning the empty list +or undefining %HASH or @ARRAY, which is the customary +way to empty out an aggregate: + + %HASH = (); # completely empty %HASH + undef %HASH; # forget %HASH ever existed + + @ARRAY = (); # completely empty @ARRAY + undef @ARRAY; # forget @ARRAY ever existed + +The EXPR can be arbitrarily complicated provided its +final operation is an element or slice of an aggregate: + + delete $ref->[$x][$y]{$key}; + delete @{$ref->[$x][$y]}{$key1, $key2, @morekeys}; + + delete $ref->[$x][$y][$index]; + delete @{$ref->[$x][$y]}[$index1, $index2, @moreindices]; + +=item die LIST +X<die> X<throw> X<exception> X<raise> X<$@> X<abort> + +C<die> raises an exception. Inside an C<eval> the error message is stuffed +into C<$@> and the C<eval> is terminated with the undefined value. +If the exception is outside of all enclosing C<eval>s, then the uncaught +exception prints LIST to C<STDERR> and exits with a non-zero value. If you +need to exit the process with a specific exit code, see L</exit>. + +Equivalent examples: + + die "Can't cd to spool: $!\n" unless chdir '/usr/spool/news'; + chdir '/usr/spool/news' or die "Can't cd to spool: $!\n" + +If the last element of LIST does not end in a newline, the current +script line number and input line number (if any) are also printed, +and a newline is supplied. Note that the "input line number" (also +known as "chunk") is subject to whatever notion of "line" happens to +be currently in effect, and is also available as the special variable +C<$.>. See L<perlvar/"$/"> and L<perlvar/"$.">. + +Hint: sometimes appending C<", stopped"> to your message will cause it +to make better sense when the string C<"at foo line 123"> is appended. +Suppose you are running script "canasta". + + die "/etc/games is no good"; + die "/etc/games is no good, stopped"; + +produce, respectively + + /etc/games is no good at canasta line 123. + /etc/games is no good, stopped at canasta line 123. + +If the output is empty and C<$@> already contains a value (typically from a +previous eval) that value is reused after appending C<"\t...propagated">. +This is useful for propagating exceptions: + + eval { ... }; + die unless $@ =~ /Expected exception/; + +If the output is empty and C<$@> contains an object reference that has a +C<PROPAGATE> method, that method will be called with additional file +and line number parameters. The return value replaces the value in +C<$@>; i.e., as if C<< $@ = eval { $@->PROPAGATE(__FILE__, __LINE__) }; >> +were called. + +If C<$@> is empty then the string C<"Died"> is used. + +If an uncaught exception results in interpreter exit, the exit code is +determined from the values of C<$!> and C<$?> with this pseudocode: + + exit $! if $!; # errno + exit $? >> 8 if $? >> 8; # child exit status + exit 255; # last resort + +The intent is to squeeze as much possible information about the likely cause +into the limited space of the system exit code. However, as C<$!> is the value +of C's C<errno>, which can be set by any system call, this means that the value +of the exit code used by C<die> can be non-predictable, so should not be relied +upon, other than to be non-zero. + +You can also call C<die> with a reference argument, and if this is trapped +within an C<eval>, C<$@> contains that reference. This permits more +elaborate exception handling using objects that maintain arbitrary state +about the exception. Such a scheme is sometimes preferable to matching +particular string values of C<$@> with regular expressions. Because C<$@> +is a global variable and C<eval> may be used within object implementations, +be careful that analyzing the error object doesn't replace the reference in +the global variable. It's easiest to make a local copy of the reference +before any manipulations. Here's an example: + + use Scalar::Util "blessed"; + + eval { ... ; die Some::Module::Exception->new( FOO => "bar" ) }; + if (my $ev_err = $@) { + if (blessed($ev_err) && $ev_err->isa("Some::Module::Exception")) { + # handle Some::Module::Exception + } + else { + # handle all other possible exceptions + } + } + +Because Perl stringifies uncaught exception messages before display, +you'll probably want to overload stringification operations on +exception objects. See L<overload> for details about that. + +You can arrange for a callback to be run just before the C<die> +does its deed, by setting the C<$SIG{__DIE__}> hook. The associated +handler is called with the error text and can change the error +message, if it sees fit, by calling C<die> again. See +L<perlvar/%SIG> for details on setting C<%SIG> entries, and +L<"eval BLOCK"> for some examples. Although this feature was +to be run only right before your program was to exit, this is not +currently so: the C<$SIG{__DIE__}> hook is currently called +even inside eval()ed blocks/strings! If one wants the hook to do +nothing in such situations, put + + die @_ if $^S; + +as the first line of the handler (see L<perlvar/$^S>). Because +this promotes strange action at a distance, this counterintuitive +behavior may be fixed in a future release. + +See also exit(), warn(), and the Carp module. + +=item do BLOCK +X<do> X<block> + +Not really a function. Returns the value of the last command in the +sequence of commands indicated by BLOCK. When modified by the C<while> or +C<until> loop modifier, executes the BLOCK once before testing the loop +condition. (On other statements the loop modifiers test the conditional +first.) + +C<do BLOCK> does I<not> count as a loop, so the loop control statements +C<next>, C<last>, or C<redo> cannot be used to leave or restart the block. +See L<perlsyn> for alternative strategies. + +=item do SUBROUTINE(LIST) +X<do> + +This form of subroutine call is deprecated. SUBROUTINE can be a bareword, +a scalar variable or a subroutine beginning with C<&>. + +=item do EXPR +X<do> + +Uses the value of EXPR as a filename and executes the contents of the +file as a Perl script. + + do 'stat.pl'; + +is just like + + eval `cat stat.pl`; + +except that it's more efficient and concise, keeps track of the current +filename for error messages, searches the C<@INC> directories, and updates +C<%INC> if the file is found. See L<perlvar/@INC> and L<perlvar/%INC> for +these variables. It also differs in that code evaluated with C<do FILENAME> +cannot see lexicals in the enclosing scope; C<eval STRING> does. It's the +same, however, in that it does reparse the file every time you call it, +so you probably don't want to do this inside a loop. + +If C<do> can read the file but cannot compile it, it returns C<undef> and sets +an error message in C<$@>. If C<do> cannot read the file, it returns undef +and sets C<$!> to the error. Always check C<$@> first, as compilation +could fail in a way that also sets C<$!>. If the file is successfully +compiled, C<do> returns the value of the last expression evaluated. + +Inclusion of library modules is better done with the +C<use> and C<require> operators, which also do automatic error checking +and raise an exception if there's a problem. + +You might like to use C<do> to read in a program configuration +file. Manual error checking can be done this way: + + # read in config files: system first, then user + for $file ("/share/prog/defaults.rc", + "$ENV{HOME}/.someprogrc") + { + unless ($return = do $file) { + warn "couldn't parse $file: $@" if $@; + warn "couldn't do $file: $!" unless defined $return; + warn "couldn't run $file" unless $return; + } + } + +=item dump LABEL +X<dump> X<core> X<undump> + +=item dump + +This function causes an immediate core dump. See also the B<-u> +command-line switch in L<perlrun>, which does the same thing. +Primarily this is so that you can use the B<undump> program (not +supplied) to turn your core dump into an executable binary after +having initialized all your variables at the beginning of the +program. When the new binary is executed it will begin by executing +a C<goto LABEL> (with all the restrictions that C<goto> suffers). +Think of it as a goto with an intervening core dump and reincarnation. +If C<LABEL> is omitted, restarts the program from the top. + +B<WARNING>: Any files opened at the time of the dump will I<not> +be open any more when the program is reincarnated, with possible +resulting confusion by Perl. + +This function is now largely obsolete, mostly because it's very hard to +convert a core file into an executable. That's why you should now invoke +it as C<CORE::dump()>, if you don't want to be warned against a possible +typo. + +Portability issues: L<perlport/dump>. + +=item each HASH +X<each> X<hash, iterator> + +=item each ARRAY +X<array, iterator> + +=item each EXPR + +When called in list context, returns a 2-element list consisting of the key +and value for the next element of a hash, or the index and value for the +next element of an array, so that you can iterate over it. When called in +scalar context, returns only the key (not the value) in a hash, or the index +in an array. + +Hash entries are returned in an apparently random order. The actual random +order is subject to change in future versions of Perl, but it is +guaranteed to be in the same order as either the C<keys> or C<values> +function would produce on the same (unmodified) hash. Since Perl +5.8.2 the ordering can be different even between different runs of Perl +for security reasons (see L<perlsec/"Algorithmic Complexity Attacks">). + +After C<each> has returned all entries from the hash or array, the next +call to C<each> returns the empty list in list context and C<undef> in +scalar context. The next call following that one restarts iteration. Each +hash or array has its own internal iterator, accessed by C<each>, C<keys>, +and C<values>. The iterator is implicitly reset when C<each> has reached +the end as just described; it can be explicitly reset by calling C<keys> or +C<values> on the hash or array. If you add or delete a hash's elements +while iterating over it, entries may be skipped or duplicated--so don't do +that. Exception: It is always safe to delete the item most recently +returned by C<each()>, so the following code works properly: + + while (($key, $value) = each %hash) { + print $key, "\n"; + delete $hash{$key}; # This is safe + } + +This prints out your environment like the printenv(1) program, +but in a different order: + + while (($key,$value) = each %ENV) { + print "$key=$value\n"; + } + +Starting with Perl 5.14, C<each> can take a scalar EXPR, which must hold +reference to an unblessed hash or array. The argument will be dereferenced +automatically. This aspect of C<each> is considered highly experimental. +The exact behaviour may change in a future version of Perl. + + while (($key,$value) = each $hashref) { ... } + +See also C<keys>, C<values>, and C<sort>. + +=item eof FILEHANDLE +X<eof> +X<end of file> +X<end-of-file> + +=item eof () + +=item eof + +Returns 1 if the next read on FILEHANDLE will return end of file I<or> if +FILEHANDLE is not open. FILEHANDLE may be an expression whose value +gives the real filehandle. (Note that this function actually +reads a character and then C<ungetc>s it, so isn't useful in an +interactive context.) Do not read from a terminal file (or call +C<eof(FILEHANDLE)> on it) after end-of-file is reached. File types such +as terminals may lose the end-of-file condition if you do. + +An C<eof> without an argument uses the last file read. Using C<eof()> +with empty parentheses is different. It refers to the pseudo file +formed from the files listed on the command line and accessed via the +C<< <> >> operator. Since C<< <> >> isn't explicitly opened, +as a normal filehandle is, an C<eof()> before C<< <> >> has been +used will cause C<@ARGV> to be examined to determine if input is +available. Similarly, an C<eof()> after C<< <> >> has returned +end-of-file will assume you are processing another C<@ARGV> list, +and if you haven't set C<@ARGV>, will read input from C<STDIN>; +see L<perlop/"I/O Operators">. + +In a C<< while (<>) >> loop, C<eof> or C<eof(ARGV)> can be used to +detect the end of each file, whereas C<eof()> will detect the end +of the very last file only. Examples: + + # reset line numbering on each input file + while (<>) { + next if /^\s*#/; # skip comments + print "$.\t$_"; + } continue { + close ARGV if eof; # Not eof()! + } + + # insert dashes just before last line of last file + while (<>) { + if (eof()) { # check for end of last file + print "--------------\n"; + } + print; + last if eof(); # needed if we're reading from a terminal + } + +Practical hint: you almost never need to use C<eof> in Perl, because the +input operators typically return C<undef> when they run out of data or +encounter an error. + +=item eval EXPR +X<eval> X<try> X<catch> X<evaluate> X<parse> X<execute> +X<error, handling> X<exception, handling> + +=item eval BLOCK + +=item eval + +In the first form, the return value of EXPR is parsed and executed as if it +were a little Perl program. The value of the expression (which is itself +determined within scalar context) is first parsed, and if there were no +errors, executed as a block within the lexical context of the current Perl +program. This means, that in particular, any outer lexical variables are +visible to it, and any package variable settings or subroutine and format +definitions remain afterwards. + +Note that the value is parsed every time the C<eval> executes. +If EXPR is omitted, evaluates C<$_>. This form is typically used to +delay parsing and subsequent execution of the text of EXPR until run time. + +If the C<unicode_eval> feature is enabled (which is the default under a +C<use 5.16> or higher declaration), EXPR or C<$_> is treated as a string of +characters, so C<use utf8> declarations have no effect, and source filters +are forbidden. In the absence of the C<unicode_eval> feature, the string +will sometimes be treated as characters and sometimes as bytes, depending +on the internal encoding, and source filters activated within the C<eval> +exhibit the erratic, but historical, behaviour of affecting some outer file +scope that is still compiling. See also the L</evalbytes> keyword, which +always treats its input as a byte stream and works properly with source +filters, and the L<feature> pragma. + +In the second form, the code within the BLOCK is parsed only once--at the +same time the code surrounding the C<eval> itself was parsed--and executed +within the context of the current Perl program. This form is typically +used to trap exceptions more efficiently than the first (see below), while +also providing the benefit of checking the code within BLOCK at compile +time. + +The final semicolon, if any, may be omitted from the value of EXPR or within +the BLOCK. + +In both forms, the value returned is the value of the last expression +evaluated inside the mini-program; a return statement may be also used, just +as with subroutines. The expression providing the return value is evaluated +in void, scalar, or list context, depending on the context of the C<eval> +itself. See L</wantarray> for more on how the evaluation context can be +determined. + +If there is a syntax error or runtime error, or a C<die> statement is +executed, C<eval> returns C<undef> in scalar context +or an empty list--or, for syntax errors, a list containing a single +undefined value--in list context, and C<$@> is set to the error +message. The discrepancy in the return values in list context is +considered a bug by some, and will probably be fixed in a future +release. If there was no error, C<$@> is set to the empty string. A +control flow operator like C<last> or C<goto> can bypass the setting of +C<$@>. Beware that using C<eval> neither silences Perl from printing +warnings to STDERR, nor does it stuff the text of warning messages into C<$@>. +To do either of those, you have to use the C<$SIG{__WARN__}> facility, or +turn off warnings inside the BLOCK or EXPR using S<C<no warnings 'all'>>. +See L</warn>, L<perlvar>, L<warnings> and L<perllexwarn>. + +Note that, because C<eval> traps otherwise-fatal errors, it is useful for +determining whether a particular feature (such as C<socket> or C<symlink>) +is implemented. It is also Perl's exception-trapping mechanism, where +the die operator is used to raise exceptions. + +If you want to trap errors when loading an XS module, some problems with +the binary interface (such as Perl version skew) may be fatal even with +C<eval> unless C<$ENV{PERL_DL_NONLAZY}> is set. See L<perlrun>. + +If the code to be executed doesn't vary, you may use the eval-BLOCK +form to trap run-time errors without incurring the penalty of +recompiling each time. The error, if any, is still returned in C<$@>. +Examples: + + # make divide-by-zero nonfatal + eval { $answer = $a / $b; }; warn $@ if $@; + + # same thing, but less efficient + eval '$answer = $a / $b'; warn $@ if $@; + + # a compile-time error + eval { $answer = }; # WRONG + + # a run-time error + eval '$answer ='; # sets $@ + +Using the C<eval{}> form as an exception trap in libraries does have some +issues. Due to the current arguably broken state of C<__DIE__> hooks, you +may wish not to trigger any C<__DIE__> hooks that user code may have installed. +You can use the C<local $SIG{__DIE__}> construct for this purpose, +as this example shows: + + # a private exception trap for divide-by-zero + eval { local $SIG{'__DIE__'}; $answer = $a / $b; }; + warn $@ if $@; + +This is especially significant, given that C<__DIE__> hooks can call +C<die> again, which has the effect of changing their error messages: + + # __DIE__ hooks may modify error messages + { + local $SIG{'__DIE__'} = + sub { (my $x = $_[0]) =~ s/foo/bar/g; die $x }; + eval { die "foo lives here" }; + print $@ if $@; # prints "bar lives here" + } + +Because this promotes action at a distance, this counterintuitive behavior +may be fixed in a future release. + +With an C<eval>, you should be especially careful to remember what's +being looked at when: + + eval $x; # CASE 1 + eval "$x"; # CASE 2 + + eval '$x'; # CASE 3 + eval { $x }; # CASE 4 + + eval "\$$x++"; # CASE 5 + $$x++; # CASE 6 + +Cases 1 and 2 above behave identically: they run the code contained in +the variable $x. (Although case 2 has misleading double quotes making +the reader wonder what else might be happening (nothing is).) Cases 3 +and 4 likewise behave in the same way: they run the code C<'$x'>, which +does nothing but return the value of $x. (Case 4 is preferred for +purely visual reasons, but it also has the advantage of compiling at +compile-time instead of at run-time.) Case 5 is a place where +normally you I<would> like to use double quotes, except that in this +particular situation, you can just use symbolic references instead, as +in case 6. + +Before Perl 5.14, the assignment to C<$@> occurred before restoration +of localised variables, which means that for your code to run on older +versions, a temporary is required if you want to mask some but not all +errors: + + # alter $@ on nefarious repugnancy only + { + my $e; + { + local $@; # protect existing $@ + eval { test_repugnancy() }; + # $@ =~ /nefarious/ and die $@; # Perl 5.14 and higher only + $@ =~ /nefarious/ and $e = $@; + } + die $e if defined $e + } + +C<eval BLOCK> does I<not> count as a loop, so the loop control statements +C<next>, C<last>, or C<redo> cannot be used to leave or restart the block. + +An C<eval ''> executed within the C<DB> package doesn't see the usual +surrounding lexical scope, but rather the scope of the first non-DB piece +of code that called it. You don't normally need to worry about this unless +you are writing a Perl debugger. + +=item evalbytes EXPR +X<evalbytes> + +=item evalbytes + +This function is like L</eval> with a string argument, except it always +parses its argument, or C<$_> if EXPR is omitted, as a string of bytes. A +string containing characters whose ordinal value exceeds 255 results in an +error. Source filters activated within the evaluated code apply to the +code itself. + +This function is only available under the C<evalbytes> feature, a +C<use v5.16> (or higher) declaration, or with a C<CORE::> prefix. See +L<feature> for more information. + +=item exec LIST +X<exec> X<execute> + +=item exec PROGRAM LIST + +The C<exec> function executes a system command I<and never returns>; +use C<system> instead of C<exec> if you want it to return. It fails and +returns false only if the command does not exist I<and> it is executed +directly instead of via your system's command shell (see below). + +Since it's a common mistake to use C<exec> instead of C<system>, Perl +warns you if there is a following statement that isn't C<die>, C<warn>, +or C<exit> (if C<-w> is set--but you always do that, right?). If you +I<really> want to follow an C<exec> with some other statement, you +can use one of these styles to avoid the warning: + + exec ('foo') or print STDERR "couldn't exec foo: $!"; + { exec ('foo') }; print STDERR "couldn't exec foo: $!"; + +If there is more than one argument in LIST, or if LIST is an array +with more than one value, calls execvp(3) with the arguments in LIST. +If there is only one scalar argument or an array with one element in it, +the argument is checked for shell metacharacters, and if there are any, +the entire argument is passed to the system's command shell for parsing +(this is C</bin/sh -c> on Unix platforms, but varies on other platforms). +If there are no shell metacharacters in the argument, it is split into +words and passed directly to C<execvp>, which is more efficient. +Examples: + + exec '/bin/echo', 'Your arguments are: ', @ARGV; + exec "sort $outfile | uniq"; + +If you don't really want to execute the first argument, but want to lie +to the program you are executing about its own name, you can specify +the program you actually want to run as an "indirect object" (without a +comma) in front of the LIST. (This always forces interpretation of the +LIST as a multivalued list, even if there is only a single scalar in +the list.) Example: + + $shell = '/bin/csh'; + exec $shell '-sh'; # pretend it's a login shell + +or, more directly, + + exec {'/bin/csh'} '-sh'; # pretend it's a login shell + +When the arguments get executed via the system shell, results are +subject to its quirks and capabilities. See L<perlop/"`STRING`"> +for details. + +Using an indirect object with C<exec> or C<system> is also more +secure. This usage (which also works fine with system()) forces +interpretation of the arguments as a multivalued list, even if the +list had just one argument. That way you're safe from the shell +expanding wildcards or splitting up words with whitespace in them. + + @args = ( "echo surprise" ); + + exec @args; # subject to shell escapes + # if @args == 1 + exec { $args[0] } @args; # safe even with one-arg list + +The first version, the one without the indirect object, ran the I<echo> +program, passing it C<"surprise"> an argument. The second version didn't; +it tried to run a program named I<"echo surprise">, didn't find it, and set +C<$?> to a non-zero value indicating failure. + +Beginning with v5.6.0, Perl attempts to flush all files opened for +output before the exec, but this may not be supported on some platforms +(see L<perlport>). To be safe, you may need to set C<$|> ($AUTOFLUSH +in English) or call the C<autoflush()> method of C<IO::Handle> on any +open handles to avoid lost output. + +Note that C<exec> will not call your C<END> blocks, nor will it invoke +C<DESTROY> methods on your objects. + +Portability issues: L<perlport/exec>. + +=item exists EXPR +X<exists> X<autovivification> + +Given an expression that specifies an element of a hash, returns true if the +specified element in the hash has ever been initialized, even if the +corresponding value is undefined. + + print "Exists\n" if exists $hash{$key}; + print "Defined\n" if defined $hash{$key}; + print "True\n" if $hash{$key}; + +exists may also be called on array elements, but its behavior is much less +obvious and is strongly tied to the use of L</delete> on arrays. B<Be aware> +that calling exists on array values is deprecated and likely to be removed in +a future version of Perl. + + print "Exists\n" if exists $array[$index]; + print "Defined\n" if defined $array[$index]; + print "True\n" if $array[$index]; + +A hash or array element can be true only if it's defined and defined only if +it exists, but the reverse doesn't necessarily hold true. + +Given an expression that specifies the name of a subroutine, +returns true if the specified subroutine has ever been declared, even +if it is undefined. Mentioning a subroutine name for exists or defined +does not count as declaring it. Note that a subroutine that does not +exist may still be callable: its package may have an C<AUTOLOAD> +method that makes it spring into existence the first time that it is +called; see L<perlsub>. + + print "Exists\n" if exists &subroutine; + print "Defined\n" if defined &subroutine; + +Note that the EXPR can be arbitrarily complicated as long as the final +operation is a hash or array key lookup or subroutine name: + + if (exists $ref->{A}->{B}->{$key}) { } + if (exists $hash{A}{B}{$key}) { } + + if (exists $ref->{A}->{B}->[$ix]) { } + if (exists $hash{A}{B}[$ix]) { } + + if (exists &{$ref->{A}{B}{$key}}) { } + +Although the mostly deeply nested array or hash will not spring into +existence just because its existence was tested, any intervening ones will. +Thus C<< $ref->{"A"} >> and C<< $ref->{"A"}->{"B"} >> will spring +into existence due to the existence test for the $key element above. +This happens anywhere the arrow operator is used, including even here: + + undef $ref; + if (exists $ref->{"Some key"}) { } + print $ref; # prints HASH(0x80d3d5c) + +This surprising autovivification in what does not at first--or even +second--glance appear to be an lvalue context may be fixed in a future +release. + +Use of a subroutine call, rather than a subroutine name, as an argument +to exists() is an error. + + exists ⊂ # OK + exists &sub(); # Error + +=item exit EXPR +X<exit> X<terminate> X<abort> + +=item exit + +Evaluates EXPR and exits immediately with that value. Example: + + $ans = <STDIN>; + exit 0 if $ans =~ /^[Xx]/; + +See also C<die>. If EXPR is omitted, exits with C<0> status. The only +universally recognized values for EXPR are C<0> for success and C<1> +for error; other values are subject to interpretation depending on the +environment in which the Perl program is running. For example, exiting +69 (EX_UNAVAILABLE) from a I<sendmail> incoming-mail filter will cause +the mailer to return the item undelivered, but that's not true everywhere. + +Don't use C<exit> to abort a subroutine if there's any chance that +someone might want to trap whatever error happened. Use C<die> instead, +which can be trapped by an C<eval>. + +The exit() function does not always exit immediately. It calls any +defined C<END> routines first, but these C<END> routines may not +themselves abort the exit. Likewise any object destructors that need to +be called are called before the real exit. C<END> routines and destructors +can change the exit status by modifying C<$?>. If this is a problem, you +can call C<POSIX:_exit($status)> to avoid END and destructor processing. +See L<perlmod> for details. + +Portability issues: L<perlport/exit>. + +=item exp EXPR +X<exp> X<exponential> X<antilog> X<antilogarithm> X<e> + +=item exp + +Returns I<e> (the natural logarithm base) to the power of EXPR. +If EXPR is omitted, gives C<exp($_)>. + +=item fcntl FILEHANDLE,FUNCTION,SCALAR +X<fcntl> + +Implements the fcntl(2) function. You'll probably have to say + + use Fcntl; + +first to get the correct constant definitions. Argument processing and +value returned work just like C<ioctl> below. +For example: + + use Fcntl; + fcntl($filehandle, F_GETFL, $packed_return_buffer) + or die "can't fcntl F_GETFL: $!"; + +You don't have to check for C<defined> on the return from C<fcntl>. +Like C<ioctl>, it maps a C<0> return from the system call into +C<"0 but true"> in Perl. This string is true in boolean context and C<0> +in numeric context. It is also exempt from the normal B<-w> warnings +on improper numeric conversions. + +Note that C<fcntl> raises an exception if used on a machine that +doesn't implement fcntl(2). See the Fcntl module or your fcntl(2) +manpage to learn what functions are available on your system. + +Here's an example of setting a filehandle named C<REMOTE> to be +non-blocking at the system level. You'll have to negotiate C<$|> +on your own, though. + + use Fcntl qw(F_GETFL F_SETFL O_NONBLOCK); + + $flags = fcntl(REMOTE, F_GETFL, 0) + or die "Can't get flags for the socket: $!\n"; + + $flags = fcntl(REMOTE, F_SETFL, $flags | O_NONBLOCK) + or die "Can't set flags for the socket: $!\n"; + +Portability issues: L<perlport/fcntl>. + +=item __FILE__ +X<__FILE__> + +A special token that returns the name of the file in which it occurs. + +=item fileno FILEHANDLE +X<fileno> + +Returns the file descriptor for a filehandle, or undefined if the +filehandle is not open. If there is no real file descriptor at the OS +level, as can happen with filehandles connected to memory objects via +C<open> with a reference for the third argument, -1 is returned. + +This is mainly useful for constructing +bitmaps for C<select> and low-level POSIX tty-handling operations. +If FILEHANDLE is an expression, the value is taken as an indirect +filehandle, generally its name. + +You can use this to find out whether two handles refer to the +same underlying descriptor: + + if (fileno(THIS) == fileno(THAT)) { + print "THIS and THAT are dups\n"; + } + +=item flock FILEHANDLE,OPERATION +X<flock> X<lock> X<locking> + +Calls flock(2), or an emulation of it, on FILEHANDLE. Returns true +for success, false on failure. Produces a fatal error if used on a +machine that doesn't implement flock(2), fcntl(2) locking, or lockf(3). +C<flock> is Perl's portable file-locking interface, although it locks +entire files only, not records. + +Two potentially non-obvious but traditional C<flock> semantics are +that it waits indefinitely until the lock is granted, and that its locks +are B<merely advisory>. Such discretionary locks are more flexible, but +offer fewer guarantees. This means that programs that do not also use +C<flock> may modify files locked with C<flock>. See L<perlport>, +your port's specific documentation, and your system-specific local manpages +for details. It's best to assume traditional behavior if you're writing +portable programs. (But if you're not, you should as always feel perfectly +free to write for your own system's idiosyncrasies (sometimes called +"features"). Slavish adherence to portability concerns shouldn't get +in the way of your getting your job done.) + +OPERATION is one of LOCK_SH, LOCK_EX, or LOCK_UN, possibly combined with +LOCK_NB. These constants are traditionally valued 1, 2, 8 and 4, but +you can use the symbolic names if you import them from the L<Fcntl> module, +either individually, or as a group using the C<:flock> tag. LOCK_SH +requests a shared lock, LOCK_EX requests an exclusive lock, and LOCK_UN +releases a previously requested lock. If LOCK_NB is bitwise-or'ed with +LOCK_SH or LOCK_EX, then C<flock> returns immediately rather than blocking +waiting for the lock; check the return status to see if you got it. + +To avoid the possibility of miscoordination, Perl now flushes FILEHANDLE +before locking or unlocking it. + +Note that the emulation built with lockf(3) doesn't provide shared +locks, and it requires that FILEHANDLE be open with write intent. These +are the semantics that lockf(3) implements. Most if not all systems +implement lockf(3) in terms of fcntl(2) locking, though, so the +differing semantics shouldn't bite too many people. + +Note that the fcntl(2) emulation of flock(3) requires that FILEHANDLE +be open with read intent to use LOCK_SH and requires that it be open +with write intent to use LOCK_EX. + +Note also that some versions of C<flock> cannot lock things over the +network; you would need to use the more system-specific C<fcntl> for +that. If you like you can force Perl to ignore your system's flock(2) +function, and so provide its own fcntl(2)-based emulation, by passing +the switch C<-Ud_flock> to the F<Configure> program when you configure +and build a new Perl. + +Here's a mailbox appender for BSD systems. + + use Fcntl qw(:flock SEEK_END); # import LOCK_* and SEEK_END constants + + sub lock { + my ($fh) = @_; + flock($fh, LOCK_EX) or die "Cannot lock mailbox - $!\n"; + + # and, in case someone appended while we were waiting... + seek($fh, 0, SEEK_END) or die "Cannot seek - $!\n"; + } + + sub unlock { + my ($fh) = @_; + flock($fh, LOCK_UN) or die "Cannot unlock mailbox - $!\n"; + } + + open(my $mbox, ">>", "/usr/spool/mail/$ENV{'USER'}") + or die "Can't open mailbox: $!"; + + lock($mbox); + print $mbox $msg,"\n\n"; + unlock($mbox); + +On systems that support a real flock(2), locks are inherited across fork() +calls, whereas those that must resort to the more capricious fcntl(2) +function lose their locks, making it seriously harder to write servers. + +See also L<DB_File> for other flock() examples. + +Portability issues: L<perlport/flock>. + +=item fork +X<fork> X<child> X<parent> + +Does a fork(2) system call to create a new process running the +same program at the same point. It returns the child pid to the +parent process, C<0> to the child process, or C<undef> if the fork is +unsuccessful. File descriptors (and sometimes locks on those descriptors) +are shared, while everything else is copied. On most systems supporting +fork(), great care has gone into making it extremely efficient (for +example, using copy-on-write technology on data pages), making it the +dominant paradigm for multitasking over the last few decades. + +Beginning with v5.6.0, Perl attempts to flush all files opened for +output before forking the child process, but this may not be supported +on some platforms (see L<perlport>). To be safe, you may need to set +C<$|> ($AUTOFLUSH in English) or call the C<autoflush()> method of +C<IO::Handle> on any open handles to avoid duplicate output. + +If you C<fork> without ever waiting on your children, you will +accumulate zombies. On some systems, you can avoid this by setting +C<$SIG{CHLD}> to C<"IGNORE">. See also L<perlipc> for more examples of +forking and reaping moribund children. + +Note that if your forked child inherits system file descriptors like +STDIN and STDOUT that are actually connected by a pipe or socket, even +if you exit, then the remote server (such as, say, a CGI script or a +backgrounded job launched from a remote shell) won't think you're done. +You should reopen those to F</dev/null> if it's any issue. + +On some platforms such as Windows, where the fork() system call is not available, +Perl can be built to emulate fork() in the Perl interpreter. The emulation is designed to, +at the level of the Perl program, be as compatible as possible with the "Unix" fork(). +However it has limitations that have to be considered in code intended to be portable. +See L<perlfork> for more details. + +Portability issues: L<perlport/fork>. + +=item format +X<format> + +Declare a picture format for use by the C<write> function. For +example: + + format Something = + Test: @<<<<<<<< @||||| @>>>>> + $str, $%, '$' . int($num) + . + + $str = "widget"; + $num = $cost/$quantity; + $~ = 'Something'; + write; + +See L<perlform> for many details and examples. + +=item formline PICTURE,LIST +X<formline> + +This is an internal function used by C<format>s, though you may call it, +too. It formats (see L<perlform>) a list of values according to the +contents of PICTURE, placing the output into the format output +accumulator, C<$^A> (or C<$ACCUMULATOR> in English). +Eventually, when a C<write> is done, the contents of +C<$^A> are written to some filehandle. You could also read C<$^A> +and then set C<$^A> back to C<"">. Note that a format typically +does one C<formline> per line of form, but the C<formline> function itself +doesn't care how many newlines are embedded in the PICTURE. This means +that the C<~> and C<~~> tokens treat the entire PICTURE as a single line. +You may therefore need to use multiple formlines to implement a single +record format, just like the C<format> compiler. + +Be careful if you put double quotes around the picture, because an C<@> +character may be taken to mean the beginning of an array name. +C<formline> always returns true. See L<perlform> for other examples. + +If you are trying to use this instead of C<write> to capture the output, +you may find it easier to open a filehandle to a scalar +(C<< open $fh, ">", \$output >>) and write to that instead. + +=item getc FILEHANDLE +X<getc> X<getchar> X<character> X<file, read> + +=item getc + +Returns the next character from the input file attached to FILEHANDLE, +or the undefined value at end of file or if there was an error (in +the latter case C<$!> is set). If FILEHANDLE is omitted, reads from +STDIN. This is not particularly efficient. However, it cannot be +used by itself to fetch single characters without waiting for the user +to hit enter. For that, try something more like: + + if ($BSD_STYLE) { + system "stty cbreak </dev/tty >/dev/tty 2>&1"; + } + else { + system "stty", '-icanon', 'eol', "\001"; + } + + $key = getc(STDIN); + + if ($BSD_STYLE) { + system "stty -cbreak </dev/tty >/dev/tty 2>&1"; + } + else { + system 'stty', 'icanon', 'eol', '^@'; # ASCII NUL + } + print "\n"; + +Determination of whether $BSD_STYLE should be set +is left as an exercise to the reader. + +The C<POSIX::getattr> function can do this more portably on +systems purporting POSIX compliance. See also the C<Term::ReadKey> +module from your nearest CPAN site; details on CPAN can be found under +L<perlmodlib/CPAN>. + +=item getlogin +X<getlogin> X<login> + +This implements the C library function of the same name, which on most +systems returns the current login from F</etc/utmp>, if any. If it +returns the empty string, use C<getpwuid>. + + $login = getlogin || getpwuid($<) || "Kilroy"; + +Do not consider C<getlogin> for authentication: it is not as +secure as C<getpwuid>. + +Portability issues: L<perlport/getlogin>. + +=item getpeername SOCKET +X<getpeername> X<peer> + +Returns the packed sockaddr address of the other end of the SOCKET +connection. + + use Socket; + $hersockaddr = getpeername(SOCK); + ($port, $iaddr) = sockaddr_in($hersockaddr); + $herhostname = gethostbyaddr($iaddr, AF_INET); + $herstraddr = inet_ntoa($iaddr); + +=item getpgrp PID +X<getpgrp> X<group> + +Returns the current process group for the specified PID. Use +a PID of C<0> to get the current process group for the +current process. Will raise an exception if used on a machine that +doesn't implement getpgrp(2). If PID is omitted, returns the process +group of the current process. Note that the POSIX version of C<getpgrp> +does not accept a PID argument, so only C<PID==0> is truly portable. + +Portability issues: L<perlport/getpgrp>. + +=item getppid +X<getppid> X<parent> X<pid> + +Returns the process id of the parent process. + +Note for Linux users: on Linux, the C functions C<getpid()> and +C<getppid()> return different values from different threads. In order to +be portable, this behavior is not reflected by the Perl-level function +C<getppid()>, that returns a consistent value across threads. If you want +to call the underlying C<getppid()>, you may use the CPAN module +C<Linux::Pid>. + +Portability issues: L<perlport/getppid>. + +=item getpriority WHICH,WHO +X<getpriority> X<priority> X<nice> + +Returns the current priority for a process, a process group, or a user. +(See L<getpriority(2)>.) Will raise a fatal exception if used on a +machine that doesn't implement getpriority(2). + +Portability issues: L<perlport/getpriority>. + +=item getpwnam NAME +X<getpwnam> X<getgrnam> X<gethostbyname> X<getnetbyname> X<getprotobyname> +X<getpwuid> X<getgrgid> X<getservbyname> X<gethostbyaddr> X<getnetbyaddr> +X<getprotobynumber> X<getservbyport> X<getpwent> X<getgrent> X<gethostent> +X<getnetent> X<getprotoent> X<getservent> X<setpwent> X<setgrent> X<sethostent> +X<setnetent> X<setprotoent> X<setservent> X<endpwent> X<endgrent> X<endhostent> +X<endnetent> X<endprotoent> X<endservent> + +=item getgrnam NAME + +=item gethostbyname NAME + +=item getnetbyname NAME + +=item getprotobyname NAME + +=item getpwuid UID + +=item getgrgid GID + +=item getservbyname NAME,PROTO + +=item gethostbyaddr ADDR,ADDRTYPE + +=item getnetbyaddr ADDR,ADDRTYPE + +=item getprotobynumber NUMBER + +=item getservbyport PORT,PROTO + +=item getpwent + +=item getgrent + +=item gethostent + +=item getnetent + +=item getprotoent + +=item getservent + +=item setpwent + +=item setgrent + +=item sethostent STAYOPEN + +=item setnetent STAYOPEN + +=item setprotoent STAYOPEN + +=item setservent STAYOPEN + +=item endpwent + +=item endgrent + +=item endhostent + +=item endnetent + +=item endprotoent + +=item endservent + +These routines are the same as their counterparts in the +system C library. In list context, the return values from the +various get routines are as follows: + + ($name,$passwd,$uid,$gid, + $quota,$comment,$gcos,$dir,$shell,$expire) = getpw* + ($name,$passwd,$gid,$members) = getgr* + ($name,$aliases,$addrtype,$length,@addrs) = gethost* + ($name,$aliases,$addrtype,$net) = getnet* + ($name,$aliases,$proto) = getproto* + ($name,$aliases,$port,$proto) = getserv* + +(If the entry doesn't exist you get an empty list.) + +The exact meaning of the $gcos field varies but it usually contains +the real name of the user (as opposed to the login name) and other +information pertaining to the user. Beware, however, that in many +system users are able to change this information and therefore it +cannot be trusted and therefore the $gcos is tainted (see +L<perlsec>). The $passwd and $shell, user's encrypted password and +login shell, are also tainted, for the same reason. + +In scalar context, you get the name, unless the function was a +lookup by name, in which case you get the other thing, whatever it is. +(If the entry doesn't exist you get the undefined value.) For example: + + $uid = getpwnam($name); + $name = getpwuid($num); + $name = getpwent(); + $gid = getgrnam($name); + $name = getgrgid($num); + $name = getgrent(); + #etc. + +In I<getpw*()> the fields $quota, $comment, and $expire are special +in that they are unsupported on many systems. If the +$quota is unsupported, it is an empty scalar. If it is supported, it +usually encodes the disk quota. If the $comment field is unsupported, +it is an empty scalar. If it is supported it usually encodes some +administrative comment about the user. In some systems the $quota +field may be $change or $age, fields that have to do with password +aging. In some systems the $comment field may be $class. The $expire +field, if present, encodes the expiration period of the account or the +password. For the availability and the exact meaning of these fields +in your system, please consult getpwnam(3) and your system's +F<pwd.h> file. You can also find out from within Perl what your +$quota and $comment fields mean and whether you have the $expire field +by using the C<Config> module and the values C<d_pwquota>, C<d_pwage>, +C<d_pwchange>, C<d_pwcomment>, and C<d_pwexpire>. Shadow password +files are supported only if your vendor has implemented them in the +intuitive fashion that calling the regular C library routines gets the +shadow versions if you're running under privilege or if there exists +the shadow(3) functions as found in System V (this includes Solaris +and Linux). Those systems that implement a proprietary shadow password +facility are unlikely to be supported. + +The $members value returned by I<getgr*()> is a space-separated list of +the login names of the members of the group. + +For the I<gethost*()> functions, if the C<h_errno> variable is supported in +C, it will be returned to you via C<$?> if the function call fails. The +C<@addrs> value returned by a successful call is a list of raw +addresses returned by the corresponding library call. In the +Internet domain, each address is four bytes long; you can unpack it +by saying something like: + + ($a,$b,$c,$d) = unpack('W4',$addr[0]); + +The Socket library makes this slightly easier: + + use Socket; + $iaddr = inet_aton("127.1"); # or whatever address + $name = gethostbyaddr($iaddr, AF_INET); + + # or going the other way + $straddr = inet_ntoa($iaddr); + +In the opposite way, to resolve a hostname to the IP address +you can write this: + + use Socket; + $packed_ip = gethostbyname("www.perl.org"); + if (defined $packed_ip) { + $ip_address = inet_ntoa($packed_ip); + } + +Make sure C<gethostbyname()> is called in SCALAR context and that +its return value is checked for definedness. + +The C<getprotobynumber> function, even though it only takes one argument, +has the precedence of a list operator, so beware: + + getprotobynumber $number eq 'icmp' # WRONG + getprotobynumber($number eq 'icmp') # actually means this + getprotobynumber($number) eq 'icmp' # better this way + +If you get tired of remembering which element of the return list +contains which return value, by-name interfaces are provided +in standard modules: C<File::stat>, C<Net::hostent>, C<Net::netent>, +C<Net::protoent>, C<Net::servent>, C<Time::gmtime>, C<Time::localtime>, +and C<User::grent>. These override the normal built-ins, supplying +versions that return objects with the appropriate names +for each field. For example: + + use File::stat; + use User::pwent; + $is_his = (stat($filename)->uid == pwent($whoever)->uid); + +Even though it looks as though they're the same method calls (uid), +they aren't, because a C<File::stat> object is different from +a C<User::pwent> object. + +Portability issues: L<perlport/getpwnam> to L<perlport/endservent>. + +=item getsockname SOCKET +X<getsockname> + +Returns the packed sockaddr address of this end of the SOCKET connection, +in case you don't know the address because you have several different +IPs that the connection might have come in on. + + use Socket; + $mysockaddr = getsockname(SOCK); + ($port, $myaddr) = sockaddr_in($mysockaddr); + printf "Connect to %s [%s]\n", + scalar gethostbyaddr($myaddr, AF_INET), + inet_ntoa($myaddr); + +=item getsockopt SOCKET,LEVEL,OPTNAME +X<getsockopt> + +Queries the option named OPTNAME associated with SOCKET at a given LEVEL. +Options may exist at multiple protocol levels depending on the socket +type, but at least the uppermost socket level SOL_SOCKET (defined in the +C<Socket> module) will exist. To query options at another level the +protocol number of the appropriate protocol controlling the option +should be supplied. For example, to indicate that an option is to be +interpreted by the TCP protocol, LEVEL should be set to the protocol +number of TCP, which you can get using C<getprotobyname>. + +The function returns a packed string representing the requested socket +option, or C<undef> on error, with the reason for the error placed in +C<$!>. Just what is in the packed string depends on LEVEL and OPTNAME; +consult getsockopt(2) for details. A common case is that the option is an +integer, in which case the result is a packed integer, which you can decode +using C<unpack> with the C<i> (or C<I>) format. + +Here's an example to test whether Nagle's algorithm is enabled on a socket: + + use Socket qw(:all); + + defined(my $tcp = getprotobyname("tcp")) + or die "Could not determine the protocol number for tcp"; + # my $tcp = IPPROTO_TCP; # Alternative + my $packed = getsockopt($socket, $tcp, TCP_NODELAY) + or die "getsockopt TCP_NODELAY: $!"; + my $nodelay = unpack("I", $packed); + print "Nagle's algorithm is turned ", $nodelay ? "off\n" : "on\n"; + +Portability issues: L<perlport/getsockopt>. + +=item given EXPR BLOCK +X<given> + +=item given BLOCK + +C<given> is analogous to the C<switch> keyword in other languages. C<given> +and C<when> are used in Perl to implement C<switch>/C<case> like statements. +Only available after Perl 5.10. For example: + + use v5.10; + given ($fruit) { + when (/apples?/) { + print "I like apples." + } + when (/oranges?/) { + print "I don't like oranges." + } + default { + print "I don't like anything" + } + } + +See L<perlsyn/"Switch statements"> for detailed information. + +=item glob EXPR +X<glob> X<wildcard> X<filename, expansion> X<expand> + +=item glob + +In list context, returns a (possibly empty) list of filename expansions on +the value of EXPR such as the standard Unix shell F</bin/csh> would do. In +scalar context, glob iterates through such filename expansions, returning +undef when the list is exhausted. This is the internal function +implementing the C<< <*.c> >> operator, but you can use it directly. If +EXPR is omitted, C<$_> is used. The C<< <*.c> >> operator is discussed in +more detail in L<perlop/"I/O Operators">. + +Note that C<glob> splits its arguments on whitespace and treats +each segment as separate pattern. As such, C<glob("*.c *.h")> +matches all files with a F<.c> or F<.h> extension. The expression +C<glob(".* *")> matches all files in the current working directory. +If you want to glob filenames that might contain whitespace, you'll +have to use extra quotes around the spacey filename to protect it. +For example, to glob filenames that have an C<e> followed by a space +followed by an C<f>, use either of: + + @spacies = <"*e f*">; + @spacies = glob '"*e f*"'; + @spacies = glob q("*e f*"); + +If you had to get a variable through, you could do this: + + @spacies = glob "'*${var}e f*'"; + @spacies = glob qq("*${var}e f*"); + +If non-empty braces are the only wildcard characters used in the +C<glob>, no filenames are matched, but potentially many strings +are returned. For example, this produces nine strings, one for +each pairing of fruits and colors: + + @many = glob "{apple,tomato,cherry}={green,yellow,red}"; + +Beginning with v5.6.0, this operator is implemented using the standard +C<File::Glob> extension. See L<File::Glob> for details, including +C<bsd_glob> which does not treat whitespace as a pattern separator. + +Portability issues: L<perlport/glob>. + +=item gmtime EXPR +X<gmtime> X<UTC> X<Greenwich> + +=item gmtime + +Works just like L</localtime> but the returned values are +localized for the standard Greenwich time zone. + +Note: When called in list context, $isdst, the last value +returned by gmtime, is always C<0>. There is no +Daylight Saving Time in GMT. + +Portability issues: L<perlport/gmtime>. + +=item goto LABEL +X<goto> X<jump> X<jmp> + +=item goto EXPR + +=item goto &NAME + +The C<goto-LABEL> form finds the statement labeled with LABEL and +resumes execution there. It can't be used to get out of a block or +subroutine given to C<sort>. It can be used to go almost anywhere +else within the dynamic scope, including out of subroutines, but it's +usually better to use some other construct such as C<last> or C<die>. +The author of Perl has never felt the need to use this form of C<goto> +(in Perl, that is; C is another matter). (The difference is that C +does not offer named loops combined with loop control. Perl does, and +this replaces most structured uses of C<goto> in other languages.) + +The C<goto-EXPR> form expects a label name, whose scope will be resolved +dynamically. This allows for computed C<goto>s per FORTRAN, but isn't +necessarily recommended if you're optimizing for maintainability: + + goto ("FOO", "BAR", "GLARCH")[$i]; + +As shown in this example, C<goto-EXPR> is exempt from the "looks like a +function" rule. A pair of parentheses following it does not (necessarily) +delimit its argument. C<goto("NE")."XT"> is equivalent to C<goto NEXT>. + +Use of C<goto-LABEL> or C<goto-EXPR> to jump into a construct is +deprecated and will issue a warning. Even then, it may not be used to +go into any construct that requires initialization, such as a +subroutine or a C<foreach> loop. It also can't be used to go into a +construct that is optimized away. + +The C<goto-&NAME> form is quite different from the other forms of +C<goto>. In fact, it isn't a goto in the normal sense at all, and +doesn't have the stigma associated with other gotos. Instead, it +exits the current subroutine (losing any changes set by local()) and +immediately calls in its place the named subroutine using the current +value of @_. This is used by C<AUTOLOAD> subroutines that wish to +load another subroutine and then pretend that the other subroutine had +been called in the first place (except that any modifications to C<@_> +in the current subroutine are propagated to the other subroutine.) +After the C<goto>, not even C<caller> will be able to tell that this +routine was called first. + +NAME needn't be the name of a subroutine; it can be a scalar variable +containing a code reference or a block that evaluates to a code +reference. + +=item grep BLOCK LIST +X<grep> + +=item grep EXPR,LIST + +This is similar in spirit to, but not the same as, grep(1) and its +relatives. In particular, it is not limited to using regular expressions. + +Evaluates the BLOCK or EXPR for each element of LIST (locally setting +C<$_> to each element) and returns the list value consisting of those +elements for which the expression evaluated to true. In scalar +context, returns the number of times the expression was true. + + @foo = grep(!/^#/, @bar); # weed out comments + +or equivalently, + + @foo = grep {!/^#/} @bar; # weed out comments + +Note that C<$_> is an alias to the list value, so it can be used to +modify the elements of the LIST. While this is useful and supported, +it can cause bizarre results if the elements of LIST are not variables. +Similarly, grep returns aliases into the original list, much as a for +loop's index variable aliases the list elements. That is, modifying an +element of a list returned by grep (for example, in a C<foreach>, C<map> +or another C<grep>) actually modifies the element in the original list. +This is usually something to be avoided when writing clear code. + +If C<$_> is lexical in the scope where the C<grep> appears (because it has +been declared with C<my $_>) then, in addition to being locally aliased to +the list elements, C<$_> keeps being lexical inside the block; i.e., it +can't be seen from the outside, avoiding any potential side-effects. + +See also L</map> for a list composed of the results of the BLOCK or EXPR. + +=item hex EXPR +X<hex> X<hexadecimal> + +=item hex + +Interprets EXPR as a hex string and returns the corresponding value. +(To convert strings that might start with either C<0>, C<0x>, or C<0b>, see +L</oct>.) If EXPR is omitted, uses C<$_>. + + print hex '0xAf'; # prints '175' + print hex 'aF'; # same + +Hex strings may only represent integers. Strings that would cause +integer overflow trigger a warning. Leading whitespace is not stripped, +unlike oct(). To present something as hex, look into L</printf>, +L</sprintf>, and L</unpack>. + +=item import LIST +X<import> + +There is no builtin C<import> function. It is just an ordinary +method (subroutine) defined (or inherited) by modules that wish to export +names to another module. The C<use> function calls the C<import> method +for the package used. See also L</use>, L<perlmod>, and L<Exporter>. + +=item index STR,SUBSTR,POSITION +X<index> X<indexOf> X<InStr> + +=item index STR,SUBSTR + +The index function searches for one string within another, but without +the wildcard-like behavior of a full regular-expression pattern match. +It returns the position of the first occurrence of SUBSTR in STR at +or after POSITION. If POSITION is omitted, starts searching from the +beginning of the string. POSITION before the beginning of the string +or after its end is treated as if it were the beginning or the end, +respectively. POSITION and the return value are based at zero. +If the substring is not found, C<index> returns -1. + +=item int EXPR +X<int> X<integer> X<truncate> X<trunc> X<floor> + +=item int + +Returns the integer portion of EXPR. If EXPR is omitted, uses C<$_>. +You should not use this function for rounding: one because it truncates +towards C<0>, and two because machine representations of floating-point +numbers can sometimes produce counterintuitive results. For example, +C<int(-6.725/0.025)> produces -268 rather than the correct -269; that's +because it's really more like -268.99999999999994315658 instead. Usually, +the C<sprintf>, C<printf>, or the C<POSIX::floor> and C<POSIX::ceil> +functions will serve you better than will int(). + +=item ioctl FILEHANDLE,FUNCTION,SCALAR +X<ioctl> + +Implements the ioctl(2) function. You'll probably first have to say + + require "sys/ioctl.ph"; # probably in $Config{archlib}/sys/ioctl.ph + +to get the correct function definitions. If F<sys/ioctl.ph> doesn't +exist or doesn't have the correct definitions you'll have to roll your +own, based on your C header files such as F<< <sys/ioctl.h> >>. +(There is a Perl script called B<h2ph> that comes with the Perl kit that +may help you in this, but it's nontrivial.) SCALAR will be read and/or +written depending on the FUNCTION; a C pointer to the string value of SCALAR +will be passed as the third argument of the actual C<ioctl> call. (If SCALAR +has no string value but does have a numeric value, that value will be +passed rather than a pointer to the string value. To guarantee this to be +true, add a C<0> to the scalar before using it.) The C<pack> and C<unpack> +functions may be needed to manipulate the values of structures used by +C<ioctl>. + +The return value of C<ioctl> (and C<fcntl>) is as follows: + + if OS returns: then Perl returns: + -1 undefined value + 0 string "0 but true" + anything else that number + +Thus Perl returns true on success and false on failure, yet you can +still easily determine the actual value returned by the operating +system: + + $retval = ioctl(...) || -1; + printf "System returned %d\n", $retval; + +The special string C<"0 but true"> is exempt from B<-w> complaints +about improper numeric conversions. + +Portability issues: L<perlport/ioctl>. + +=item join EXPR,LIST +X<join> + +Joins the separate strings of LIST into a single string with fields +separated by the value of EXPR, and returns that new string. Example: + + $rec = join(':', $login,$passwd,$uid,$gid,$gcos,$home,$shell); + +Beware that unlike C<split>, C<join> doesn't take a pattern as its +first argument. Compare L</split>. + +=item keys HASH +X<keys> X<key> + +=item keys ARRAY + +=item keys EXPR + +Returns a list consisting of all the keys of the named hash, or the indices +of an array. (In scalar context, returns the number of keys or indices.) + +The keys of a hash are returned in an apparently random order. The actual +random order is subject to change in future versions of Perl, but it +is guaranteed to be the same order as either the C<values> or C<each> +function produces (given that the hash has not been modified). Since +Perl 5.8.1 the ordering can be different even between different runs of +Perl for security reasons (see L<perlsec/"Algorithmic Complexity +Attacks">). + +As a side effect, calling keys() resets the internal interator of the HASH or ARRAY +(see L</each>). In particular, calling keys() in void context resets +the iterator with no other overhead. + +Here is yet another way to print your environment: + + @keys = keys %ENV; + @values = values %ENV; + while (@keys) { + print pop(@keys), '=', pop(@values), "\n"; + } + +or how about sorted by key: + + foreach $key (sort(keys %ENV)) { + print $key, '=', $ENV{$key}, "\n"; + } + +The returned values are copies of the original keys in the hash, so +modifying them will not affect the original hash. Compare L</values>. + +To sort a hash by value, you'll need to use a C<sort> function. +Here's a descending numeric sort of a hash by its values: + + foreach $key (sort { $hash{$b} <=> $hash{$a} } keys %hash) { + printf "%4d %s\n", $hash{$key}, $key; + } + +Used as an lvalue, C<keys> allows you to increase the number of hash buckets +allocated for the given hash. This can gain you a measure of efficiency if +you know the hash is going to get big. (This is similar to pre-extending +an array by assigning a larger number to $#array.) If you say + + keys %hash = 200; + +then C<%hash> will have at least 200 buckets allocated for it--256 of them, +in fact, since it rounds up to the next power of two. These +buckets will be retained even if you do C<%hash = ()>, use C<undef +%hash> if you want to free the storage while C<%hash> is still in scope. +You can't shrink the number of buckets allocated for the hash using +C<keys> in this way (but you needn't worry about doing this by accident, +as trying has no effect). C<keys @array> in an lvalue context is a syntax +error. + +Starting with Perl 5.14, C<keys> can take a scalar EXPR, which must contain +a reference to an unblessed hash or array. The argument will be +dereferenced automatically. This aspect of C<keys> is considered highly +experimental. The exact behaviour may change in a future version of Perl. + + for (keys $hashref) { ... } + for (keys $obj->get_arrayref) { ... } + +See also C<each>, C<values>, and C<sort>. + +=item kill SIGNAL, LIST +X<kill> X<signal> + +Sends a signal to a list of processes. Returns the number of +processes successfully signaled (which is not necessarily the +same as the number actually killed). + + $cnt = kill 1, $child1, $child2; + kill 9, @goners; + +If SIGNAL is zero, no signal is sent to the process, but C<kill> +checks whether it's I<possible> to send a signal to it (that +means, to be brief, that the process is owned by the same user, or we are +the super-user). This is useful to check that a child process is still +alive (even if only as a zombie) and hasn't changed its UID. See +L<perlport> for notes on the portability of this construct. + +Unlike in the shell, if SIGNAL is negative, it kills process groups instead +of processes. That means you usually want to use positive not negative signals. +You may also use a signal name in quotes. + +The behavior of kill when a I<PROCESS> number is zero or negative depends on +the operating system. For example, on POSIX-conforming systems, zero will +signal the current process group and -1 will signal all processes. + +See L<perlipc/"Signals"> for more details. + +On some platforms such as Windows where the fork() system call is not available. +Perl can be built to emulate fork() at the interpreter level. +This emulation has limitations related to kill that have to be considered, +for code running on Windows and in code intended to be portable. + +See L<perlfork> for more details. + +Portability issues: L<perlport/kill>. + +=item last LABEL +X<last> X<break> + +=item last + +The C<last> command is like the C<break> statement in C (as used in +loops); it immediately exits the loop in question. If the LABEL is +omitted, the command refers to the innermost enclosing loop. The +C<continue> block, if any, is not executed: + + LINE: while (<STDIN>) { + last LINE if /^$/; # exit when done with header + #... + } + +C<last> cannot be used to exit a block that returns a value such as +C<eval {}>, C<sub {}>, or C<do {}>, and should not be used to exit +a grep() or map() operation. + +Note that a block by itself is semantically identical to a loop +that executes once. Thus C<last> can be used to effect an early +exit out of such a block. + +See also L</continue> for an illustration of how C<last>, C<next>, and +C<redo> work. + +=item lc EXPR +X<lc> X<lowercase> + +=item lc + +Returns a lowercased version of EXPR. This is the internal function +implementing the C<\L> escape in double-quoted strings. + +If EXPR is omitted, uses C<$_>. + +What gets returned depends on several factors: + +=over + +=item If C<use bytes> is in effect: + +=over + +=item On EBCDIC platforms + +The results are what the C language system call C<tolower()> returns. + +=item On ASCII platforms + +The results follow ASCII semantics. Only characters C<A-Z> change, to C<a-z> +respectively. + +=back + +=item Otherwise, If EXPR has the UTF8 flag set + +Unicode semantics are used for the case change. + +=item Otherwise, if C<use locale> is in effect + +Respects current LC_CTYPE locale. See L<perllocale>. + +=item Otherwise, if C<use feature 'unicode_strings'> is in effect: + +Unicode semantics are used for the case change. + +=item Otherwise: + +=over + +=item On EBCDIC platforms + +The results are what the C language system call C<tolower()> returns. + +=item On ASCII platforms + +ASCII semantics are used for the case change. The lowercase of any character +outside the ASCII range is the character itself. + +=back + +=back + +=item lcfirst EXPR +X<lcfirst> X<lowercase> + +=item lcfirst + +Returns the value of EXPR with the first character lowercased. This +is the internal function implementing the C<\l> escape in +double-quoted strings. + +If EXPR is omitted, uses C<$_>. + +This function behaves the same way under various pragmata, such as in a locale, +as L</lc> does. + +=item length EXPR +X<length> X<size> + +=item length + +Returns the length in I<characters> of the value of EXPR. If EXPR is +omitted, returns the length of C<$_>. If EXPR is undefined, returns +C<undef>. + +This function cannot be used on an entire array or hash to find out how +many elements these have. For that, use C<scalar @array> and C<scalar keys +%hash>, respectively. + +Like all Perl character operations, length() normally deals in logical +characters, not physical bytes. For how many bytes a string encoded as +UTF-8 would take up, use C<length(Encode::encode_utf8(EXPR))> (you'll have +to C<use Encode> first). See L<Encode> and L<perlunicode>. + +=item __LINE__ +X<__LINE__> + +A special token that compiles to the current line number. + +=item link OLDFILE,NEWFILE +X<link> + +Creates a new filename linked to the old filename. Returns true for +success, false otherwise. + +Portability issues: L<perlport/link>. + +=item listen SOCKET,QUEUESIZE +X<listen> + +Does the same thing that the listen(2) system call does. Returns true if +it succeeded, false otherwise. See the example in +L<perlipc/"Sockets: Client/Server Communication">. + +=item local EXPR +X<local> + +You really probably want to be using C<my> instead, because C<local> isn't +what most people think of as "local". See +L<perlsub/"Private Variables via my()"> for details. + +A local modifies the listed variables to be local to the enclosing +block, file, or eval. If more than one value is listed, the list must +be placed in parentheses. See L<perlsub/"Temporary Values via local()"> +for details, including issues with tied arrays and hashes. + +The C<delete local EXPR> construct can also be used to localize the deletion +of array/hash elements to the current block. +See L<perlsub/"Localized deletion of elements of composite types">. + +=item localtime EXPR +X<localtime> X<ctime> + +=item localtime + +Converts a time as returned by the time function to a 9-element list +with the time analyzed for the local time zone. Typically used as +follows: + + # 0 1 2 3 4 5 6 7 8 + ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = + localtime(time); + +All list elements are numeric and come straight out of the C `struct +tm'. C<$sec>, C<$min>, and C<$hour> are the seconds, minutes, and hours +of the specified time. + +C<$mday> is the day of the month and C<$mon> the month in +the range C<0..11>, with 0 indicating January and 11 indicating December. +This makes it easy to get a month name from a list: + + my @abbr = qw( Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec ); + print "$abbr[$mon] $mday"; + # $mon=9, $mday=18 gives "Oct 18" + +C<$year> is the number of years since 1900, B<not> just the last two digits +of the year. That is, C<$year> is C<123> in year 2023. The proper way +to get a 4-digit year is simply: + + $year += 1900; + +Otherwise you create non-Y2K-compliant programs--and you wouldn't want +to do that, would you? + +To get the last two digits of the year (e.g., "01" in 2001) do: + + $year = sprintf("%02d", $year % 100); + +C<$wday> is the day of the week, with 0 indicating Sunday and 3 indicating +Wednesday. C<$yday> is the day of the year, in the range C<0..364> +(or C<0..365> in leap years.) + +C<$isdst> is true if the specified time occurs during Daylight Saving +Time, false otherwise. + +If EXPR is omitted, C<localtime()> uses the current time (as returned +by time(3)). + +In scalar context, C<localtime()> returns the ctime(3) value: + + $now_string = localtime; # e.g., "Thu Oct 13 04:54:34 1994" + +This scalar value is B<not> locale-dependent but is a Perl builtin. For GMT +instead of local time use the L</gmtime> builtin. See also the +C<Time::Local> module (for converting seconds, minutes, hours, and such back to +the integer value returned by time()), and the L<POSIX> module's strftime(3) +and mktime(3) functions. + +To get somewhat similar but locale-dependent date strings, set up your +locale environment variables appropriately (please see L<perllocale>) and +try for example: + + use POSIX qw(strftime); + $now_string = strftime "%a %b %e %H:%M:%S %Y", localtime; + # or for GMT formatted appropriately for your locale: + $now_string = strftime "%a %b %e %H:%M:%S %Y", gmtime; + +Note that the C<%a> and C<%b>, the short forms of the day of the week +and the month of the year, may not necessarily be three characters wide. + +The L<Time::gmtime> and L<Time::localtime> modules provide a convenient, +by-name access mechanism to the gmtime() and localtime() functions, +respectively. + +For a comprehensive date and time representation look at the +L<DateTime> module on CPAN. + +Portability issues: L<perlport/localtime>. + +=item lock THING +X<lock> + +This function places an advisory lock on a shared variable or referenced +object contained in I<THING> until the lock goes out of scope. + +The value returned is the scalar itself, if the argument is a scalar, or a +reference, if the argument is a hash, array or subroutine. + +lock() is a "weak keyword" : this means that if you've defined a function +by this name (before any calls to it), that function will be called +instead. If you are not under C<use threads::shared> this does nothing. +See L<threads::shared>. + +=item log EXPR +X<log> X<logarithm> X<e> X<ln> X<base> + +=item log + +Returns the natural logarithm (base I<e>) of EXPR. If EXPR is omitted, +returns the log of C<$_>. To get the +log of another base, use basic algebra: +The base-N log of a number is equal to the natural log of that number +divided by the natural log of N. For example: + + sub log10 { + my $n = shift; + return log($n)/log(10); + } + +See also L</exp> for the inverse operation. + +=item lstat FILEHANDLE +X<lstat> + +=item lstat EXPR + +=item lstat DIRHANDLE + +=item lstat + +Does the same thing as the C<stat> function (including setting the +special C<_> filehandle) but stats a symbolic link instead of the file +the symbolic link points to. If symbolic links are unimplemented on +your system, a normal C<stat> is done. For much more detailed +information, please see the documentation for C<stat>. + +If EXPR is omitted, stats C<$_>. + +Portability issues: L<perlport/lstat>. + +=item m// + +The match operator. See L<perlop/"Regexp Quote-Like Operators">. + +=item map BLOCK LIST +X<map> + +=item map EXPR,LIST + +Evaluates the BLOCK or EXPR for each element of LIST (locally setting +C<$_> to each element) and returns the list value composed of the +results of each such evaluation. In scalar context, returns the +total number of elements so generated. Evaluates BLOCK or EXPR in +list context, so each element of LIST may produce zero, one, or +more elements in the returned value. + + @chars = map(chr, @numbers); + +translates a list of numbers to the corresponding characters. + + my @squares = map { $_ * $_ } @numbers; + +translates a list of numbers to their squared values. + + my @squares = map { $_ > 5 ? ($_ * $_) : () } @numbers; + +shows that number of returned elements can differ from the number of +input elements. To omit an element, return an empty list (). +This could also be achieved by writing + + my @squares = map { $_ * $_ } grep { $_ > 5 } @numbers; + +which makes the intention more clear. + +Map always returns a list, which can be +assigned to a hash such that the elements +become key/value pairs. See L<perldata> for more details. + + %hash = map { get_a_key_for($_) => $_ } @array; + +is just a funny way to write + + %hash = (); + foreach (@array) { + $hash{get_a_key_for($_)} = $_; + } + +Note that C<$_> is an alias to the list value, so it can be used to +modify the elements of the LIST. While this is useful and supported, +it can cause bizarre results if the elements of LIST are not variables. +Using a regular C<foreach> loop for this purpose would be clearer in +most cases. See also L</grep> for an array composed of those items of +the original list for which the BLOCK or EXPR evaluates to true. + +If C<$_> is lexical in the scope where the C<map> appears (because it has +been declared with C<my $_>), then, in addition to being locally aliased to +the list elements, C<$_> keeps being lexical inside the block; that is, it +can't be seen from the outside, avoiding any potential side-effects. + +C<{> starts both hash references and blocks, so C<map { ...> could be either +the start of map BLOCK LIST or map EXPR, LIST. Because Perl doesn't look +ahead for the closing C<}> it has to take a guess at which it's dealing with +based on what it finds just after the C<{>. Usually it gets it right, but if it +doesn't it won't realize something is wrong until it gets to the C<}> and +encounters the missing (or unexpected) comma. The syntax error will be +reported close to the C<}>, but you'll need to change something near the C<{> +such as using a unary C<+> to give Perl some help: + + %hash = map { "\L$_" => 1 } @array # perl guesses EXPR. wrong + %hash = map { +"\L$_" => 1 } @array # perl guesses BLOCK. right + %hash = map { ("\L$_" => 1) } @array # this also works + %hash = map { lc($_) => 1 } @array # as does this. + %hash = map +( lc($_) => 1 ), @array # this is EXPR and works! + + %hash = map ( lc($_), 1 ), @array # evaluates to (1, @array) + +or to force an anon hash constructor use C<+{>: + + @hashes = map +{ lc($_) => 1 }, @array # EXPR, so needs comma at end + +to get a list of anonymous hashes each with only one entry apiece. + +=item mkdir FILENAME,MASK +X<mkdir> X<md> X<directory, create> + +=item mkdir FILENAME + +=item mkdir + +Creates the directory specified by FILENAME, with permissions +specified by MASK (as modified by C<umask>). If it succeeds it +returns true; otherwise it returns false and sets C<$!> (errno). +MASK defaults to 0777 if omitted, and FILENAME defaults +to C<$_> if omitted. + +In general, it is better to create directories with a permissive MASK +and let the user modify that with their C<umask> than it is to supply +a restrictive MASK and give the user no way to be more permissive. +The exceptions to this rule are when the file or directory should be +kept private (mail files, for instance). The perlfunc(1) entry on +C<umask> discusses the choice of MASK in more detail. + +Note that according to the POSIX 1003.1-1996 the FILENAME may have any +number of trailing slashes. Some operating and filesystems do not get +this right, so Perl automatically removes all trailing slashes to keep +everyone happy. + +To recursively create a directory structure, look at +the C<mkpath> function of the L<File::Path> module. + +=item msgctl ID,CMD,ARG +X<msgctl> + +Calls the System V IPC function msgctl(2). You'll probably have to say + + use IPC::SysV; + +first to get the correct constant definitions. If CMD is C<IPC_STAT>, +then ARG must be a variable that will hold the returned C<msqid_ds> +structure. Returns like C<ioctl>: the undefined value for error, +C<"0 but true"> for zero, or the actual return value otherwise. See also +L<perlipc/"SysV IPC"> and the documentation for C<IPC::SysV> and +C<IPC::Semaphore>. + +Portability issues: L<perlport/msgctl>. + +=item msgget KEY,FLAGS +X<msgget> + +Calls the System V IPC function msgget(2). Returns the message queue +id, or C<undef> on error. See also +L<perlipc/"SysV IPC"> and the documentation for C<IPC::SysV> and +C<IPC::Msg>. + +Portability issues: L<perlport/msgget>. + +=item msgrcv ID,VAR,SIZE,TYPE,FLAGS +X<msgrcv> + +Calls the System V IPC function msgrcv to receive a message from +message queue ID into variable VAR with a maximum message size of +SIZE. Note that when a message is received, the message type as a +native long integer will be the first thing in VAR, followed by the +actual message. This packing may be opened with C<unpack("l! a*")>. +Taints the variable. Returns true if successful, false +on error. See also L<perlipc/"SysV IPC"> and the documentation for +C<IPC::SysV> and C<IPC::SysV::Msg>. + +Portability issues: L<perlport/msgrcv>. + +=item msgsnd ID,MSG,FLAGS +X<msgsnd> + +Calls the System V IPC function msgsnd to send the message MSG to the +message queue ID. MSG must begin with the native long integer message +type, be followed by the length of the actual message, and then finally +the message itself. This kind of packing can be achieved with +C<pack("l! a*", $type, $message)>. Returns true if successful, +false on error. See also the C<IPC::SysV> +and C<IPC::SysV::Msg> documentation. + +Portability issues: L<perlport/msgsnd>. + +=item my EXPR +X<my> + +=item my TYPE EXPR + +=item my EXPR : ATTRS + +=item my TYPE EXPR : ATTRS + +A C<my> declares the listed variables to be local (lexically) to the +enclosing block, file, or C<eval>. If more than one value is listed, +the list must be placed in parentheses. + +The exact semantics and interface of TYPE and ATTRS are still +evolving. TYPE is currently bound to the use of the C<fields> pragma, +and attributes are handled using the C<attributes> pragma, or starting +from Perl 5.8.0 also via the C<Attribute::Handlers> module. See +L<perlsub/"Private Variables via my()"> for details, and L<fields>, +L<attributes>, and L<Attribute::Handlers>. + +=item next LABEL +X<next> X<continue> + +=item next + +The C<next> command is like the C<continue> statement in C; it starts +the next iteration of the loop: + + LINE: while (<STDIN>) { + next LINE if /^#/; # discard comments + #... + } + +Note that if there were a C<continue> block on the above, it would get +executed even on discarded lines. If LABEL is omitted, the command +refers to the innermost enclosing loop. + +C<next> cannot be used to exit a block which returns a value such as +C<eval {}>, C<sub {}>, or C<do {}>, and should not be used to exit +a grep() or map() operation. + +Note that a block by itself is semantically identical to a loop +that executes once. Thus C<next> will exit such a block early. + +See also L</continue> for an illustration of how C<last>, C<next>, and +C<redo> work. + +=item no MODULE VERSION LIST +X<no declarations> +X<unimporting> + +=item no MODULE VERSION + +=item no MODULE LIST + +=item no MODULE + +=item no VERSION + +See the C<use> function, of which C<no> is the opposite. + +=item oct EXPR +X<oct> X<octal> X<hex> X<hexadecimal> X<binary> X<bin> + +=item oct + +Interprets EXPR as an octal string and returns the corresponding +value. (If EXPR happens to start off with C<0x>, interprets it as a +hex string. If EXPR starts off with C<0b>, it is interpreted as a +binary string. Leading whitespace is ignored in all three cases.) +The following will handle decimal, binary, octal, and hex in standard +Perl notation: + + $val = oct($val) if $val =~ /^0/; + +If EXPR is omitted, uses C<$_>. To go the other way (produce a number +in octal), use sprintf() or printf(): + + $dec_perms = (stat("filename"))[2] & 07777; + $oct_perm_str = sprintf "%o", $perms; + +The oct() function is commonly used when a string such as C<644> needs +to be converted into a file mode, for example. Although Perl +automatically converts strings into numbers as needed, this automatic +conversion assumes base 10. + +Leading white space is ignored without warning, as too are any trailing +non-digits, such as a decimal point (C<oct> only handles non-negative +integers, not negative integers or floating point). + +=item open FILEHANDLE,EXPR +X<open> X<pipe> X<file, open> X<fopen> + +=item open FILEHANDLE,MODE,EXPR + +=item open FILEHANDLE,MODE,EXPR,LIST + +=item open FILEHANDLE,MODE,REFERENCE + +=item open FILEHANDLE + +Opens the file whose filename is given by EXPR, and associates it with +FILEHANDLE. + +Simple examples to open a file for reading: + + open(my $fh, "<", "input.txt") + or die "cannot open < input.txt: $!"; + +and for writing: + + open(my $fh, ">", "output.txt") + or die "cannot open > output.txt: $!"; + +(The following is a comprehensive reference to open(): for a gentler +introduction you may consider L<perlopentut>.) + +If FILEHANDLE is an undefined scalar variable (or array or hash element), a +new filehandle is autovivified, meaning that the variable is assigned a +reference to a newly allocated anonymous filehandle. Otherwise if +FILEHANDLE is an expression, its value is the real filehandle. (This is +considered a symbolic reference, so C<use strict "refs"> should I<not> be +in effect.) + +If EXPR is omitted, the global (package) scalar variable of the same +name as the FILEHANDLE contains the filename. (Note that lexical +variables--those declared with C<my> or C<state>--will not work for this +purpose; so if you're using C<my> or C<state>, specify EXPR in your +call to open.) + +If three (or more) arguments are specified, the open mode (including +optional encoding) in the second argument are distinct from the filename in +the third. If MODE is C<< < >> or nothing, the file is opened for input. +If MODE is C<< > >>, the file is opened for output, with existing files +first being truncated ("clobbered") and nonexisting files newly created. +If MODE is C<<< >> >>>, the file is opened for appending, again being +created if necessary. + +You can put a C<+> in front of the C<< > >> or C<< < >> to +indicate that you want both read and write access to the file; thus +C<< +< >> is almost always preferred for read/write updates--the +C<< +> >> mode would clobber the file first. You cant usually use +either read-write mode for updating textfiles, since they have +variable-length records. See the B<-i> switch in L<perlrun> for a +better approach. The file is created with permissions of C<0666> +modified by the process's C<umask> value. + +These various prefixes correspond to the fopen(3) modes of C<r>, +C<r+>, C<w>, C<w+>, C<a>, and C<a+>. + +In the one- and two-argument forms of the call, the mode and filename +should be concatenated (in that order), preferably separated by white +space. You can--but shouldn't--omit the mode in these forms when that mode +is C<< < >>. It is always safe to use the two-argument form of C<open> if +the filename argument is a known literal. + +For three or more arguments if MODE is C<|->, the filename is +interpreted as a command to which output is to be piped, and if MODE +is C<-|>, the filename is interpreted as a command that pipes +output to us. In the two-argument (and one-argument) form, one should +replace dash (C<->) with the command. +See L<perlipc/"Using open() for IPC"> for more examples of this. +(You are not allowed to C<open> to a command that pipes both in I<and> +out, but see L<IPC::Open2>, L<IPC::Open3>, and +L<perlipc/"Bidirectional Communication with Another Process"> for +alternatives.) + +In the form of pipe opens taking three or more arguments, if LIST is specified +(extra arguments after the command name) then LIST becomes arguments +to the command invoked if the platform supports it. The meaning of +C<open> with more than three arguments for non-pipe modes is not yet +defined, but experimental "layers" may give extra LIST arguments +meaning. + +In the two-argument (and one-argument) form, opening C<< <- >> +or C<-> opens STDIN and opening C<< >- >> opens STDOUT. + +You may (and usually should) use the three-argument form of open to specify +I/O layers (sometimes referred to as "disciplines") to apply to the handle +that affect how the input and output are processed (see L<open> and +L<PerlIO> for more details). For example: + + open(my $fh, "<:encoding(UTF-8)", "filename") + || die "can't open UTF-8 encoded filename: $!"; + +opens the UTF8-encoded file containing Unicode characters; +see L<perluniintro>. Note that if layers are specified in the +three-argument form, then default layers stored in ${^OPEN} (see L<perlvar>; +usually set by the B<open> pragma or the switch B<-CioD>) are ignored. +Those layers will also be ignored if you specifying a colon with no name +following it. In that case the default layer for the operating system +(:raw on Unix, :crlf on Windows) is used. + +Open returns nonzero on success, the undefined value otherwise. If +the C<open> involved a pipe, the return value happens to be the pid of +the subprocess. + +If you're running Perl on a system that distinguishes between text +files and binary files, then you should check out L</binmode> for tips +for dealing with this. The key distinction between systems that need +C<binmode> and those that don't is their text file formats. Systems +like Unix, Mac OS, and Plan 9, that end lines with a single +character and encode that character in C as C<"\n"> do not +need C<binmode>. The rest need it. + +When opening a file, it's seldom a good idea to continue +if the request failed, so C<open> is frequently used with +C<die>. Even if C<die> won't do what you want (say, in a CGI script, +where you want to format a suitable error message (but there are +modules that can help with that problem)) always check +the return value from opening a file. + +As a special case the three-argument form with a read/write mode and the third +argument being C<undef>: + + open(my $tmp, "+>", undef) or die ... + +opens a filehandle to an anonymous temporary file. Also using C<< +< >> +works for symmetry, but you really should consider writing something +to the temporary file first. You will need to seek() to do the +reading. + +Since v5.8.0, Perl has built using PerlIO by default. Unless you've +changed this (such as building Perl with C<Configure -Uuseperlio>), you can +open filehandles directly to Perl scalars via: + + open($fh, ">", \$variable) || .. + +To (re)open C<STDOUT> or C<STDERR> as an in-memory file, close it first: + + close STDOUT; + open(STDOUT, ">", \$variable) + or die "Can't open STDOUT: $!"; + +General examples: + + $ARTICLE = 100; + open(ARTICLE) or die "Can't find article $ARTICLE: $!\n"; + while (<ARTICLE>) {... + + open(LOG, ">>/usr/spool/news/twitlog"); # (log is reserved) + # if the open fails, output is discarded + + open(my $dbase, "+<", "dbase.mine") # open for update + or die "Can't open 'dbase.mine' for update: $!"; + + open(my $dbase, "+<dbase.mine") # ditto + or die "Can't open 'dbase.mine' for update: $!"; + + open(ARTICLE, "-|", "caesar <$article") # decrypt article + or die "Can't start caesar: $!"; + + open(ARTICLE, "caesar <$article |") # ditto + or die "Can't start caesar: $!"; + + open(EXTRACT, "|sort >Tmp$$") # $$ is our process id + or die "Can't start sort: $!"; + + # in-memory files + open(MEMORY, ">", \$var) + or die "Can't open memory file: $!"; + print MEMORY "foo!\n"; # output will appear in $var + + # process argument list of files along with any includes + + foreach $file (@ARGV) { + process($file, "fh00"); + } + + sub process { + my($filename, $input) = @_; + $input++; # this is a string increment + unless (open($input, "<", $filename)) { + print STDERR "Can't open $filename: $!\n"; + return; + } + + local $_; + while (<$input>) { # note use of indirection + if (/^#include "(.*)"/) { + process($1, $input); + next; + } + #... # whatever + } + } + +See L<perliol> for detailed info on PerlIO. + +You may also, in the Bourne shell tradition, specify an EXPR beginning +with C<< >& >>, in which case the rest of the string is interpreted +as the name of a filehandle (or file descriptor, if numeric) to be +duped (as C<dup(2)>) and opened. You may use C<&> after C<< > >>, +C<<< >> >>>, C<< < >>, C<< +> >>, C<<< +>> >>>, and C<< +< >>. +The mode you specify should match the mode of the original filehandle. +(Duping a filehandle does not take into account any existing contents +of IO buffers.) If you use the three-argument form, then you can pass either a +number, the name of a filehandle, or the normal "reference to a glob". + +Here is a script that saves, redirects, and restores C<STDOUT> and +C<STDERR> using various methods: + + #!/usr/bin/perl + open(my $oldout, ">&STDOUT") or die "Can't dup STDOUT: $!"; + open(OLDERR, ">&", \*STDERR) or die "Can't dup STDERR: $!"; + + open(STDOUT, '>', "foo.out") or die "Can't redirect STDOUT: $!"; + open(STDERR, ">&STDOUT") or die "Can't dup STDOUT: $!"; + + select STDERR; $| = 1; # make unbuffered + select STDOUT; $| = 1; # make unbuffered + + print STDOUT "stdout 1\n"; # this works for + print STDERR "stderr 1\n"; # subprocesses too + + open(STDOUT, ">&", $oldout) or die "Can't dup \$oldout: $!"; + open(STDERR, ">&OLDERR") or die "Can't dup OLDERR: $!"; + + print STDOUT "stdout 2\n"; + print STDERR "stderr 2\n"; + +If you specify C<< '<&=X' >>, where C<X> is a file descriptor number +or a filehandle, then Perl will do an equivalent of C's C<fdopen> of +that file descriptor (and not call C<dup(2)>); this is more +parsimonious of file descriptors. For example: + + # open for input, reusing the fileno of $fd + open(FILEHANDLE, "<&=$fd") + +or + + open(FILEHANDLE, "<&=", $fd) + +or + + # open for append, using the fileno of OLDFH + open(FH, ">>&=", OLDFH) + +or + + open(FH, ">>&=OLDFH") + +Being parsimonious on filehandles is also useful (besides being +parsimonious) for example when something is dependent on file +descriptors, like for example locking using flock(). If you do just +C<< open(A, ">>&B") >>, the filehandle A will not have the same file +descriptor as B, and therefore flock(A) will not flock(B) nor vice +versa. But with C<< open(A, ">>&=B") >>, the filehandles will share +the same underlying system file descriptor. + +Note that under Perls older than 5.8.0, Perl uses the standard C library's' +fdopen() to implement the C<=> functionality. On many Unix systems, +fdopen() fails when file descriptors exceed a certain value, typically 255. +For Perls 5.8.0 and later, PerlIO is (most often) the default. + +You can see whether your Perl was built with PerlIO by running C<perl -V> +and looking for the C<useperlio=> line. If C<useperlio> is C<define>, you +have PerlIO; otherwise you don't. + +If you open a pipe on the command C<-> (that is, specify either C<|-> or C<-|> +with the one- or two-argument forms of C<open>), +an implicit C<fork> is done, so C<open> returns twice: in the parent +process it returns the pid +of the child process, and in the child process it returns (a defined) C<0>. +Use C<defined($pid)> or C<//> to determine whether the open was successful. + +For example, use either + + $child_pid = open(FROM_KID, "-|") // die "can't fork: $!"; + +or + $child_pid = open(TO_KID, "|-") // die "can't fork: $!"; + +followed by + + if ($child_pid) { + # am the parent: + # either write TO_KID or else read FROM_KID + ... + wait $child_pid; + } else { + # am the child; use STDIN/STDOUT normally + ... + exit; + } + +The filehandle behaves normally for the parent, but I/O to that +filehandle is piped from/to the STDOUT/STDIN of the child process. +In the child process, the filehandle isn't opened--I/O happens from/to +the new STDOUT/STDIN. Typically this is used like the normal +piped open when you want to exercise more control over just how the +pipe command gets executed, such as when running setuid and +you don't want to have to scan shell commands for metacharacters. + +The following blocks are more or less equivalent: + + open(FOO, "|tr '[a-z]' '[A-Z]'"); + open(FOO, "|-", "tr '[a-z]' '[A-Z]'"); + open(FOO, "|-") || exec 'tr', '[a-z]', '[A-Z]'; + open(FOO, "|-", "tr", '[a-z]', '[A-Z]'); + + open(FOO, "cat -n '$file'|"); + open(FOO, "-|", "cat -n '$file'"); + open(FOO, "-|") || exec "cat", "-n", $file; + open(FOO, "-|", "cat", "-n", $file); + +The last two examples in each block show the pipe as "list form", which is +not yet supported on all platforms. A good rule of thumb is that if +your platform has a real C<fork()> (in other words, if your platform is +Unix, including Linux and MacOS X), you can use the list form. You would +want to use the list form of the pipe so you can pass literal arguments +to the command without risk of the shell interpreting any shell metacharacters +in them. However, this also bars you from opening pipes to commands +that intentionally contain shell metacharacters, such as: + + open(FOO, "|cat -n | expand -4 | lpr") + // die "Can't open pipeline to lpr: $!"; + +See L<perlipc/"Safe Pipe Opens"> for more examples of this. + +Beginning with v5.6.0, Perl will attempt to flush all files opened for +output before any operation that may do a fork, but this may not be +supported on some platforms (see L<perlport>). To be safe, you may need +to set C<$|> ($AUTOFLUSH in English) or call the C<autoflush()> method +of C<IO::Handle> on any open handles. + +On systems that support a close-on-exec flag on files, the flag will +be set for the newly opened file descriptor as determined by the value +of C<$^F>. See L<perlvar/$^F>. + +Closing any piped filehandle causes the parent process to wait for the +child to finish, then returns the status value in C<$?> and +C<${^CHILD_ERROR_NATIVE}>. + +The filename passed to the one- and two-argument forms of open() will +have leading and trailing whitespace deleted and normal +redirection characters honored. This property, known as "magic open", +can often be used to good effect. A user could specify a filename of +F<"rsh cat file |">, or you could change certain filenames as needed: + + $filename =~ s/(.*\.gz)\s*$/gzip -dc < $1|/; + open(FH, $filename) or die "Can't open $filename: $!"; + +Use the three-argument form to open a file with arbitrary weird characters in it, + + open(FOO, "<", $file) + || die "can't open < $file: $!"; + +otherwise it's necessary to protect any leading and trailing whitespace: + + $file =~ s#^(\s)#./$1#; + open(FOO, "< $file\0") + || die "open failed: $!"; + +(this may not work on some bizarre filesystems). One should +conscientiously choose between the I<magic> and I<three-argument> form +of open(): + + open(IN, $ARGV[0]) || die "can't open $ARGV[0]: $!"; + +will allow the user to specify an argument of the form C<"rsh cat file |">, +but will not work on a filename that happens to have a trailing space, while + + open(IN, "<", $ARGV[0]) + || die "can't open < $ARGV[0]: $!"; + +will have exactly the opposite restrictions. + +If you want a "real" C C<open> (see L<open(2)> on your system), then you +should use the C<sysopen> function, which involves no such magic (but may +use subtly different filemodes than Perl open(), which is mapped to C +fopen()). This is another way to protect your filenames from +interpretation. For example: + + use IO::Handle; + sysopen(HANDLE, $path, O_RDWR|O_CREAT|O_EXCL) + or die "sysopen $path: $!"; + $oldfh = select(HANDLE); $| = 1; select($oldfh); + print HANDLE "stuff $$\n"; + seek(HANDLE, 0, 0); + print "File contains: ", <HANDLE>; + +Using the constructor from the C<IO::Handle> package (or one of its +subclasses, such as C<IO::File> or C<IO::Socket>), you can generate anonymous +filehandles that have the scope of the variables used to hold them, then +automatically (but silently) close once their reference counts become +zero, typically at scope exit: + + use IO::File; + #... + sub read_myfile_munged { + my $ALL = shift; + # or just leave it undef to autoviv + my $handle = IO::File->new; + open($handle, "<", "myfile") or die "myfile: $!"; + $first = <$handle> + or return (); # Automatically closed here. + mung($first) or die "mung failed"; # Or here. + return (first, <$handle>) if $ALL; # Or here. + return $first; # Or here. + } + +B<WARNING:> The previous example has a bug because the automatic +close that happens when the refcount on C<handle> does not +properly detect and report failures. I<Always> close the handle +yourself and inspect the return value. + + close($handle) + || warn "close failed: $!"; + +See L</seek> for some details about mixing reading and writing. + +Portability issues: L<perlport/open>. + +=item opendir DIRHANDLE,EXPR +X<opendir> + +Opens a directory named EXPR for processing by C<readdir>, C<telldir>, +C<seekdir>, C<rewinddir>, and C<closedir>. Returns true if successful. +DIRHANDLE may be an expression whose value can be used as an indirect +dirhandle, usually the real dirhandle name. If DIRHANDLE is an undefined +scalar variable (or array or hash element), the variable is assigned a +reference to a new anonymous dirhandle; that is, it's autovivified. +DIRHANDLEs have their own namespace separate from FILEHANDLEs. + +See the example at C<readdir>. + +=item ord EXPR +X<ord> X<encoding> + +=item ord + +Returns the numeric value of the first character of EXPR. +If EXPR is an empty string, returns 0. If EXPR is omitted, uses C<$_>. +(Note I<character>, not byte.) + +For the reverse, see L</chr>. +See L<perlunicode> for more about Unicode. + +=item our EXPR +X<our> X<global> + +=item our TYPE EXPR + +=item our EXPR : ATTRS + +=item our TYPE EXPR : ATTRS + +C<our> associates a simple name with a package variable in the current +package for use within the current scope. When C<use strict 'vars'> is in +effect, C<our> lets you use declared global variables without qualifying +them with package names, within the lexical scope of the C<our> declaration. +In this way C<our> differs from C<use vars>, which is package-scoped. + +Unlike C<my> or C<state>, which allocates storage for a variable and +associates a simple name with that storage for use within the current +scope, C<our> associates a simple name with a package (read: global) +variable in the current package, for use within the current lexical scope. +In other words, C<our> has the same scoping rules as C<my> or C<state>, but +does not necessarily create a variable. + +If more than one value is listed, the list must be placed +in parentheses. + + our $foo; + our($bar, $baz); + +An C<our> declaration declares a global variable that will be visible +across its entire lexical scope, even across package boundaries. The +package in which the variable is entered is determined at the point +of the declaration, not at the point of use. This means the following +behavior holds: + + package Foo; + our $bar; # declares $Foo::bar for rest of lexical scope + $bar = 20; + + package Bar; + print $bar; # prints 20, as it refers to $Foo::bar + +Multiple C<our> declarations with the same name in the same lexical +scope are allowed if they are in different packages. If they happen +to be in the same package, Perl will emit warnings if you have asked +for them, just like multiple C<my> declarations. Unlike a second +C<my> declaration, which will bind the name to a fresh variable, a +second C<our> declaration in the same package, in the same scope, is +merely redundant. + + use warnings; + package Foo; + our $bar; # declares $Foo::bar for rest of lexical scope + $bar = 20; + + package Bar; + our $bar = 30; # declares $Bar::bar for rest of lexical scope + print $bar; # prints 30 + + our $bar; # emits warning but has no other effect + print $bar; # still prints 30 + +An C<our> declaration may also have a list of attributes associated +with it. + +The exact semantics and interface of TYPE and ATTRS are still +evolving. TYPE is currently bound to the use of C<fields> pragma, +and attributes are handled using the C<attributes> pragma, or starting +from Perl 5.8.0 also via the C<Attribute::Handlers> module. See +L<perlsub/"Private Variables via my()"> for details, and L<fields>, +L<attributes>, and L<Attribute::Handlers>. + +=item pack TEMPLATE,LIST +X<pack> + +Takes a LIST of values and converts it into a string using the rules +given by the TEMPLATE. The resulting string is the concatenation of +the converted values. Typically, each converted value looks +like its machine-level representation. For example, on 32-bit machines +an integer may be represented by a sequence of 4 bytes, which will in +Perl be presented as a string that's 4 characters long. + +See L<perlpacktut> for an introduction to this function. + +The TEMPLATE is a sequence of characters that give the order and type +of values, as follows: + + a A string with arbitrary binary data, will be null padded. + A A text (ASCII) string, will be space padded. + Z A null-terminated (ASCIZ) string, will be null padded. + + b A bit string (ascending bit order inside each byte, + like vec()). + B A bit string (descending bit order inside each byte). + h A hex string (low nybble first). + H A hex string (high nybble first). + + c A signed char (8-bit) value. + C An unsigned char (octet) value. + W An unsigned char value (can be greater than 255). + + s A signed short (16-bit) value. + S An unsigned short value. + + l A signed long (32-bit) value. + L An unsigned long value. + + q A signed quad (64-bit) value. + Q An unsigned quad value. + (Quads are available only if your system supports 64-bit + integer values _and_ if Perl has been compiled to support + those. Raises an exception otherwise.) + + i A signed integer value. + I A unsigned integer value. + (This 'integer' is _at_least_ 32 bits wide. Its exact + size depends on what a local C compiler calls 'int'.) + + n An unsigned short (16-bit) in "network" (big-endian) order. + N An unsigned long (32-bit) in "network" (big-endian) order. + v An unsigned short (16-bit) in "VAX" (little-endian) order. + V An unsigned long (32-bit) in "VAX" (little-endian) order. + + j A Perl internal signed integer value (IV). + J A Perl internal unsigned integer value (UV). + + f A single-precision float in native format. + d A double-precision float in native format. + + F A Perl internal floating-point value (NV) in native format + D A float of long-double precision in native format. + (Long doubles are available only if your system supports + long double values _and_ if Perl has been compiled to + support those. Raises an exception otherwise.) + + p A pointer to a null-terminated string. + P A pointer to a structure (fixed-length string). + + u A uuencoded string. + U A Unicode character number. Encodes to a character in char- + acter mode and UTF-8 (or UTF-EBCDIC in EBCDIC platforms) in + byte mode. + + w A BER compressed integer (not an ASN.1 BER, see perlpacktut + for details). Its bytes represent an unsigned integer in + base 128, most significant digit first, with as few digits + as possible. Bit eight (the high bit) is set on each byte + except the last. + + x A null byte (a.k.a ASCII NUL, "\000", chr(0)) + X Back up a byte. + @ Null-fill or truncate to absolute position, counted from the + start of the innermost ()-group. + . Null-fill or truncate to absolute position specified by + the value. + ( Start of a ()-group. + +One or more modifiers below may optionally follow certain letters in the +TEMPLATE (the second column lists letters for which the modifier is valid): + + ! sSlLiI Forces native (short, long, int) sizes instead + of fixed (16-/32-bit) sizes. + + xX Make x and X act as alignment commands. + + nNvV Treat integers as signed instead of unsigned. + + @. Specify position as byte offset in the internal + representation of the packed string. Efficient but + dangerous. + + > sSiIlLqQ Force big-endian byte-order on the type. + jJfFdDpP (The "big end" touches the construct.) + + < sSiIlLqQ Force little-endian byte-order on the type. + jJfFdDpP (The "little end" touches the construct.) + +The C<< > >> and C<< < >> modifiers can also be used on C<()> groups +to force a particular byte-order on all components in that group, +including all its subgroups. + +The following rules apply: + +=over + +=item * + +Each letter may optionally be followed by a number indicating the repeat +count. A numeric repeat count may optionally be enclosed in brackets, as +in C<pack("C[80]", @arr)>. The repeat count gobbles that many values from +the LIST when used with all format types other than C<a>, C<A>, C<Z>, C<b>, +C<B>, C<h>, C<H>, C<@>, C<.>, C<x>, C<X>, and C<P>, where it means +something else, described below. Supplying a C<*> for the repeat count +instead of a number means to use however many items are left, except for: + +=over + +=item * + +C<@>, C<x>, and C<X>, where it is equivalent to C<0>. + +=item * + +<.>, where it means relative to the start of the string. + +=item * + +C<u>, where it is equivalent to 1 (or 45, which here is equivalent). + +=back + +One can replace a numeric repeat count with a template letter enclosed in +brackets to use the packed byte length of the bracketed template for the +repeat count. + +For example, the template C<x[L]> skips as many bytes as in a packed long, +and the template C<"$t X[$t] $t"> unpacks twice whatever $t (when +variable-expanded) unpacks. If the template in brackets contains alignment +commands (such as C<x![d]>), its packed length is calculated as if the +start of the template had the maximal possible alignment. + +When used with C<Z>, a C<*> as the repeat count is guaranteed to add a +trailing null byte, so the resulting string is always one byte longer than +the byte length of the item itself. + +When used with C<@>, the repeat count represents an offset from the start +of the innermost C<()> group. + +When used with C<.>, the repeat count determines the starting position to +calculate the value offset as follows: + +=over + +=item * + +If the repeat count is C<0>, it's relative to the current position. + +=item * + +If the repeat count is C<*>, the offset is relative to the start of the +packed string. + +=item * + +And if it's an integer I<n>, the offset is relative to the start of the +I<n>th innermost C<( )> group, or to the start of the string if I<n> is +bigger then the group level. + +=back + +The repeat count for C<u> is interpreted as the maximal number of bytes +to encode per line of output, with 0, 1 and 2 replaced by 45. The repeat +count should not be more than 65. + +=item * + +The C<a>, C<A>, and C<Z> types gobble just one value, but pack it as a +string of length count, padding with nulls or spaces as needed. When +unpacking, C<A> strips trailing whitespace and nulls, C<Z> strips everything +after the first null, and C<a> returns data with no stripping at all. + +If the value to pack is too long, the result is truncated. If it's too +long and an explicit count is provided, C<Z> packs only C<$count-1> bytes, +followed by a null byte. Thus C<Z> always packs a trailing null, except +when the count is 0. + +=item * + +Likewise, the C<b> and C<B> formats pack a string that's that many bits long. +Each such format generates 1 bit of the result. These are typically followed +by a repeat count like C<B8> or C<B64>. + +Each result bit is based on the least-significant bit of the corresponding +input character, i.e., on C<ord($char)%2>. In particular, characters C<"0"> +and C<"1"> generate bits 0 and 1, as do characters C<"\000"> and C<"\001">. + +Starting from the beginning of the input string, each 8-tuple +of characters is converted to 1 character of output. With format C<b>, +the first character of the 8-tuple determines the least-significant bit of a +character; with format C<B>, it determines the most-significant bit of +a character. + +If the length of the input string is not evenly divisible by 8, the +remainder is packed as if the input string were padded by null characters +at the end. Similarly during unpacking, "extra" bits are ignored. + +If the input string is longer than needed, remaining characters are ignored. + +A C<*> for the repeat count uses all characters of the input field. +On unpacking, bits are converted to a string of C<0>s and C<1>s. + +=item * + +The C<h> and C<H> formats pack a string that many nybbles (4-bit groups, +representable as hexadecimal digits, C<"0".."9"> C<"a".."f">) long. + +For each such format, pack() generates 4 bits of result. +With non-alphabetical characters, the result is based on the 4 least-significant +bits of the input character, i.e., on C<ord($char)%16>. In particular, +characters C<"0"> and C<"1"> generate nybbles 0 and 1, as do bytes +C<"\000"> and C<"\001">. For characters C<"a".."f"> and C<"A".."F">, the result +is compatible with the usual hexadecimal digits, so that C<"a"> and +C<"A"> both generate the nybble C<0xA==10>. Use only these specific hex +characters with this format. + +Starting from the beginning of the template to pack(), each pair +of characters is converted to 1 character of output. With format C<h>, the +first character of the pair determines the least-significant nybble of the +output character; with format C<H>, it determines the most-significant +nybble. + +If the length of the input string is not even, it behaves as if padded by +a null character at the end. Similarly, "extra" nybbles are ignored during +unpacking. + +If the input string is longer than needed, extra characters are ignored. + +A C<*> for the repeat count uses all characters of the input field. For +unpack(), nybbles are converted to a string of hexadecimal digits. + +=item * + +The C<p> format packs a pointer to a null-terminated string. You are +responsible for ensuring that the string is not a temporary value, as that +could potentially get deallocated before you got around to using the packed +result. The C<P> format packs a pointer to a structure of the size indicated +by the length. A null pointer is created if the corresponding value for +C<p> or C<P> is C<undef>; similarly with unpack(), where a null pointer +unpacks into C<undef>. + +If your system has a strange pointer size--meaning a pointer is neither as +big as an int nor as big as a long--it may not be possible to pack or +unpack pointers in big- or little-endian byte order. Attempting to do +so raises an exception. + +=item * + +The C</> template character allows packing and unpacking of a sequence of +items where the packed structure contains a packed item count followed by +the packed items themselves. This is useful when the structure you're +unpacking has encoded the sizes or repeat counts for some of its fields +within the structure itself as separate fields. + +For C<pack>, you write I<length-item>C</>I<sequence-item>, and the +I<length-item> describes how the length value is packed. Formats likely +to be of most use are integer-packing ones like C<n> for Java strings, +C<w> for ASN.1 or SNMP, and C<N> for Sun XDR. + +For C<pack>, I<sequence-item> may have a repeat count, in which case +the minimum of that and the number of available items is used as the argument +for I<length-item>. If it has no repeat count or uses a '*', the number +of available items is used. + +For C<unpack>, an internal stack of integer arguments unpacked so far is +used. You write C</>I<sequence-item> and the repeat count is obtained by +popping off the last element from the stack. The I<sequence-item> must not +have a repeat count. + +If I<sequence-item> refers to a string type (C<"A">, C<"a">, or C<"Z">), +the I<length-item> is the string length, not the number of strings. With +an explicit repeat count for pack, the packed string is adjusted to that +length. For example: + + This code: gives this result: + + unpack("W/a", "\004Gurusamy") ("Guru") + unpack("a3/A A*", "007 Bond J ") (" Bond", "J") + unpack("a3 x2 /A A*", "007: Bond, J.") ("Bond, J", ".") + + pack("n/a* w/a","hello,","world") "\000\006hello,\005world" + pack("a/W2", ord("a") .. ord("z")) "2ab" + +The I<length-item> is not returned explicitly from C<unpack>. + +Supplying a count to the I<length-item> format letter is only useful with +C<A>, C<a>, or C<Z>. Packing with a I<length-item> of C<a> or C<Z> may +introduce C<"\000"> characters, which Perl does not regard as legal in +numeric strings. + +=item * + +The integer types C<s>, C<S>, C<l>, and C<L> may be +followed by a C<!> modifier to specify native shorts or +longs. As shown in the example above, a bare C<l> means +exactly 32 bits, although the native C<long> as seen by the local C compiler +may be larger. This is mainly an issue on 64-bit platforms. You can +see whether using C<!> makes any difference this way: + + printf "format s is %d, s! is %d\n", + length pack("s"), length pack("s!"); + + printf "format l is %d, l! is %d\n", + length pack("l"), length pack("l!"); + + +C<i!> and C<I!> are also allowed, but only for completeness' sake: +they are identical to C<i> and C<I>. + +The actual sizes (in bytes) of native shorts, ints, longs, and long +longs on the platform where Perl was built are also available from +the command line: + + $ perl -V:{short,int,long{,long}}size + shortsize='2'; + intsize='4'; + longsize='4'; + longlongsize='8'; + +or programmatically via the C<Config> module: + + use Config; + print $Config{shortsize}, "\n"; + print $Config{intsize}, "\n"; + print $Config{longsize}, "\n"; + print $Config{longlongsize}, "\n"; + +C<$Config{longlongsize}> is undefined on systems without +long long support. + +=item * + +The integer formats C<s>, C<S>, C<i>, C<I>, C<l>, C<L>, C<j>, and C<J> are +inherently non-portable between processors and operating systems because +they obey native byteorder and endianness. For example, a 4-byte integer +0x12345678 (305419896 decimal) would be ordered natively (arranged in and +handled by the CPU registers) into bytes as + + 0x12 0x34 0x56 0x78 # big-endian + 0x78 0x56 0x34 0x12 # little-endian + +Basically, Intel and VAX CPUs are little-endian, while everybody else, +including Motorola m68k/88k, PPC, Sparc, HP PA, Power, and Cray, are +big-endian. Alpha and MIPS can be either: Digital/Compaq uses (well, used) +them in little-endian mode, but SGI/Cray uses them in big-endian mode. + +The names I<big-endian> and I<little-endian> are comic references to the +egg-eating habits of the little-endian Lilliputians and the big-endian +Blefuscudians from the classic Jonathan Swift satire, I<Gulliver's Travels>. +This entered computer lingo via the paper "On Holy Wars and a Plea for +Peace" by Danny Cohen, USC/ISI IEN 137, April 1, 1980. + +Some systems may have even weirder byte orders such as + + 0x56 0x78 0x12 0x34 + 0x34 0x12 0x78 0x56 + +You can determine your system endianness with this incantation: + + printf("%#02x ", $_) for unpack("W*", pack L=>0x12345678); + +The byteorder on the platform where Perl was built is also available +via L<Config>: + + use Config; + print "$Config{byteorder}\n"; + +or from the command line: + + $ perl -V:byteorder + +Byteorders C<"1234"> and C<"12345678"> are little-endian; C<"4321"> +and C<"87654321"> are big-endian. + +For portably packed integers, either use the formats C<n>, C<N>, C<v>, +and C<V> or else use the C<< > >> and C<< < >> modifiers described +immediately below. See also L<perlport>. + +=item * + +Starting with Perl 5.9.2, integer and floating-point formats, along with +the C<p> and C<P> formats and C<()> groups, may all be followed by the +C<< > >> or C<< < >> endianness modifiers to respectively enforce big- +or little-endian byte-order. These modifiers are especially useful +given how C<n>, C<N>, C<v>, and C<V> don't cover signed integers, +64-bit integers, or floating-point values. + +Here are some concerns to keep in mind when using an endianness modifier: + +=over + +=item * + +Exchanging signed integers between different platforms works only +when all platforms store them in the same format. Most platforms store +signed integers in two's-complement notation, so usually this is not an issue. + +=item * + +The C<< > >> or C<< < >> modifiers can only be used on floating-point +formats on big- or little-endian machines. Otherwise, attempting to +use them raises an exception. + +=item * + +Forcing big- or little-endian byte-order on floating-point values for +data exchange can work only if all platforms use the same +binary representation such as IEEE floating-point. Even if all +platforms are using IEEE, there may still be subtle differences. Being able +to use C<< > >> or C<< < >> on floating-point values can be useful, +but also dangerous if you don't know exactly what you're doing. +It is not a general way to portably store floating-point values. + +=item * + +When using C<< > >> or C<< < >> on a C<()> group, this affects +all types inside the group that accept byte-order modifiers, +including all subgroups. It is silently ignored for all other +types. You are not allowed to override the byte-order within a group +that already has a byte-order modifier suffix. + +=back + +=item * + +Real numbers (floats and doubles) are in native machine format only. +Due to the multiplicity of floating-point formats and the lack of a +standard "network" representation for them, no facility for interchange has been +made. This means that packed floating-point data written on one machine +may not be readable on another, even if both use IEEE floating-point +arithmetic (because the endianness of the memory representation is not part +of the IEEE spec). See also L<perlport>. + +If you know I<exactly> what you're doing, you can use the C<< > >> or C<< < >> +modifiers to force big- or little-endian byte-order on floating-point values. + +Because Perl uses doubles (or long doubles, if configured) internally for +all numeric calculation, converting from double into float and thence +to double again loses precision, so C<unpack("f", pack("f", $foo)>) +will not in general equal $foo. + +=item * + +Pack and unpack can operate in two modes: character mode (C<C0> mode) where +the packed string is processed per character, and UTF-8 mode (C<U0> mode) +where the packed string is processed in its UTF-8-encoded Unicode form on +a byte-by-byte basis. Character mode is the default unless the format string +starts with C<U>. You can always switch mode mid-format with an explicit +C<C0> or C<U0> in the format. This mode remains in effect until the next +mode change, or until the end of the C<()> group it (directly) applies to. + +Using C<C0> to get Unicode characters while using C<U0> to get I<non>-Unicode +bytes is not necessarily obvious. Probably only the first of these +is what you want: + + $ perl -CS -E 'say "\x{3B1}\x{3C9}"' | + perl -CS -ne 'printf "%v04X\n", $_ for unpack("C0A*", $_)' + 03B1.03C9 + $ perl -CS -E 'say "\x{3B1}\x{3C9}"' | + perl -CS -ne 'printf "%v02X\n", $_ for unpack("U0A*", $_)' + CE.B1.CF.89 + $ perl -CS -E 'say "\x{3B1}\x{3C9}"' | + perl -C0 -ne 'printf "%v02X\n", $_ for unpack("C0A*", $_)' + CE.B1.CF.89 + $ perl -CS -E 'say "\x{3B1}\x{3C9}"' | + perl -C0 -ne 'printf "%v02X\n", $_ for unpack("U0A*", $_)' + C3.8E.C2.B1.C3.8F.C2.89 + +Those examples also illustrate that you should not try to use +C<pack>/C<unpack> as a substitute for the L<Encode> module. + +=item * + +You must yourself do any alignment or padding by inserting, for example, +enough C<"x">es while packing. There is no way for pack() and unpack() +to know where characters are going to or coming from, so they +handle their output and input as flat sequences of characters. + +=item * + +A C<()> group is a sub-TEMPLATE enclosed in parentheses. A group may +take a repeat count either as postfix, or for unpack(), also via the C</> +template character. Within each repetition of a group, positioning with +C<@> starts over at 0. Therefore, the result of + + pack("@1A((@2A)@3A)", qw[X Y Z]) + +is the string C<"\0X\0\0YZ">. + +=item * + +C<x> and C<X> accept the C<!> modifier to act as alignment commands: they +jump forward or back to the closest position aligned at a multiple of C<count> +characters. For example, to pack() or unpack() a C structure like + + struct { + char c; /* one signed, 8-bit character */ + double d; + char cc[2]; + } + +one may need to use the template C<c x![d] d c[2]>. This assumes that +doubles must be aligned to the size of double. + +For alignment commands, a C<count> of 0 is equivalent to a C<count> of 1; +both are no-ops. + +=item * + +C<n>, C<N>, C<v> and C<V> accept the C<!> modifier to +represent signed 16-/32-bit integers in big-/little-endian order. +This is portable only when all platforms sharing packed data use the +same binary representation for signed integers; for example, when all +platforms use two's-complement representation. + +=item * + +Comments can be embedded in a TEMPLATE using C<#> through the end of line. +White space can separate pack codes from each other, but modifiers and +repeat counts must follow immediately. Breaking complex templates into +individual line-by-line components, suitably annotated, can do as much to +improve legibility and maintainability of pack/unpack formats as C</x> can +for complicated pattern matches. + +=item * + +If TEMPLATE requires more arguments than pack() is given, pack() +assumes additional C<""> arguments. If TEMPLATE requires fewer arguments +than given, extra arguments are ignored. + +=back + +Examples: + + $foo = pack("WWWW",65,66,67,68); + # foo eq "ABCD" + $foo = pack("W4",65,66,67,68); + # same thing + $foo = pack("W4",0x24b6,0x24b7,0x24b8,0x24b9); + # same thing with Unicode circled letters. + $foo = pack("U4",0x24b6,0x24b7,0x24b8,0x24b9); + # same thing with Unicode circled letters. You don't get the + # UTF-8 bytes because the U at the start of the format caused + # a switch to U0-mode, so the UTF-8 bytes get joined into + # characters + $foo = pack("C0U4",0x24b6,0x24b7,0x24b8,0x24b9); + # foo eq "\xe2\x92\xb6\xe2\x92\xb7\xe2\x92\xb8\xe2\x92\xb9" + # This is the UTF-8 encoding of the string in the + # previous example + + $foo = pack("ccxxcc",65,66,67,68); + # foo eq "AB\0\0CD" + + # NOTE: The examples above featuring "W" and "c" are true + # only on ASCII and ASCII-derived systems such as ISO Latin 1 + # and UTF-8. On EBCDIC systems, the first example would be + # $foo = pack("WWWW",193,194,195,196); + + $foo = pack("s2",1,2); + # "\001\000\002\000" on little-endian + # "\000\001\000\002" on big-endian + + $foo = pack("a4","abcd","x","y","z"); + # "abcd" + + $foo = pack("aaaa","abcd","x","y","z"); + # "axyz" + + $foo = pack("a14","abcdefg"); + # "abcdefg\0\0\0\0\0\0\0" + + $foo = pack("i9pl", gmtime); + # a real struct tm (on my system anyway) + + $utmp_template = "Z8 Z8 Z16 L"; + $utmp = pack($utmp_template, @utmp1); + # a struct utmp (BSDish) + + @utmp2 = unpack($utmp_template, $utmp); + # "@utmp1" eq "@utmp2" + + sub bintodec { + unpack("N", pack("B32", substr("0" x 32 . shift, -32))); + } + + $foo = pack('sx2l', 12, 34); + # short 12, two zero bytes padding, long 34 + $bar = pack('s@4l', 12, 34); + # short 12, zero fill to position 4, long 34 + # $foo eq $bar + $baz = pack('s.l', 12, 4, 34); + # short 12, zero fill to position 4, long 34 + + $foo = pack('nN', 42, 4711); + # pack big-endian 16- and 32-bit unsigned integers + $foo = pack('S>L>', 42, 4711); + # exactly the same + $foo = pack('s<l<', -42, 4711); + # pack little-endian 16- and 32-bit signed integers + $foo = pack('(sl)<', -42, 4711); + # exactly the same + +The same template may generally also be used in unpack(). + +=item package NAMESPACE + +=item package NAMESPACE VERSION +X<package> X<module> X<namespace> X<version> + +=item package NAMESPACE BLOCK + +=item package NAMESPACE VERSION BLOCK +X<package> X<module> X<namespace> X<version> + +Declares the BLOCK or the rest of the compilation unit as being in the +given namespace. The scope of the package declaration is either the +supplied code BLOCK or, in the absence of a BLOCK, from the declaration +itself through the end of current scope (the enclosing block, file, or +C<eval>). That is, the forms without a BLOCK are operative through the end +of the current scope, just like the C<my>, C<state>, and C<our> operators. +All unqualified dynamic identifiers in this scope will be in the given +namespace, except where overridden by another C<package> declaration or +when they're one of the special identifiers that qualify into C<main::>, +like C<STDOUT>, C<ARGV>, C<ENV>, and the punctuation variables. + +A package statement affects dynamic variables only, including those +you've used C<local> on, but I<not> lexical variables, which are created +with C<my>, C<state>, or C<our>. Typically it would be the first +declaration in a file included by C<require> or C<use>. You can switch into a +package in more than one place, since this only determines which default +symbol table the compiler uses for the rest of that block. You can refer to +identifiers in other packages than the current one by prefixing the identifier +with the package name and a double colon, as in C<$SomePack::var> +or C<ThatPack::INPUT_HANDLE>. If package name is omitted, the C<main> +package as assumed. That is, C<$::sail> is equivalent to +C<$main::sail> (as well as to C<$main'sail>, still seen in ancient +code, mostly from Perl 4). + +If VERSION is provided, C<package> sets the C<$VERSION> variable in the given +namespace to a L<version> object with the VERSION provided. VERSION must be a +"strict" style version number as defined by the L<version> module: a positive +decimal number (integer or decimal-fraction) without exponentiation or else a +dotted-decimal v-string with a leading 'v' character and at least three +components. You should set C<$VERSION> only once per package. + +See L<perlmod/"Packages"> for more information about packages, modules, +and classes. See L<perlsub> for other scoping issues. + +=item pipe READHANDLE,WRITEHANDLE +X<pipe> + +Opens a pair of connected pipes like the corresponding system call. +Note that if you set up a loop of piped processes, deadlock can occur +unless you are very careful. In addition, note that Perl's pipes use +IO buffering, so you may need to set C<$|> to flush your WRITEHANDLE +after each command, depending on the application. + +See L<IPC::Open2>, L<IPC::Open3>, and +L<perlipc/"Bidirectional Communication with Another Process"> +for examples of such things. + +On systems that support a close-on-exec flag on files, that flag is set +on all newly opened file descriptors whose C<fileno>s are I<higher> than +the current value of $^F (by default 2 for C<STDERR>). See L<perlvar/$^F>. + +=item __PACKAGE__ +X<__PACKAGE__> + +A special token that returns the name of the package in which it occurs. + +=item pop ARRAY +X<pop> X<stack> + +=item pop EXPR + +=item pop + +Pops and returns the last value of the array, shortening the array by +one element. + +Returns the undefined value if the array is empty, although this may also +happen at other times. If ARRAY is omitted, pops the C<@ARGV> array in the +main program, but the C<@_> array in subroutines, just like C<shift>. + +Starting with Perl 5.14, C<pop> can take a scalar EXPR, which must hold a +reference to an unblessed array. The argument will be dereferenced +automatically. This aspect of C<pop> is considered highly experimental. +The exact behaviour may change in a future version of Perl. + +=item pos SCALAR +X<pos> X<match, position> + +=item pos + +Returns the offset of where the last C<m//g> search left off for the +variable in question (C<$_> is used when the variable is not +specified). Note that 0 is a valid match offset. C<undef> indicates +that the search position is reset (usually due to match failure, but +can also be because no match has yet been run on the scalar). + +C<pos> directly accesses the location used by the regexp engine to +store the offset, so assigning to C<pos> will change that offset, and +so will also influence the C<\G> zero-width assertion in regular +expressions. Both of these effects take place for the next match, so +you can't affect the position with C<pos> during the current match, +such as in C<(?{pos() = 5})> or C<s//pos() = 5/e>. + +Setting C<pos> also resets the I<matched with zero-length> flag, described +under L<perlre/"Repeated Patterns Matching a Zero-length Substring">. + +Because a failed C<m//gc> match doesn't reset the offset, the return +from C<pos> won't change either in this case. See L<perlre> and +L<perlop>. + +=item print FILEHANDLE LIST +X<print> + +=item print FILEHANDLE + +=item print LIST + +=item print + +Prints a string or a list of strings. Returns true if successful. +FILEHANDLE may be a scalar variable containing the name of or a reference +to the filehandle, thus introducing one level of indirection. (NOTE: If +FILEHANDLE is a variable and the next token is a term, it may be +misinterpreted as an operator unless you interpose a C<+> or put +parentheses around the arguments.) If FILEHANDLE is omitted, prints to the +last selected (see L</select>) output handle. If LIST is omitted, prints +C<$_> to the currently selected output handle. To use FILEHANDLE alone to +print the content of C<$_> to it, you must use a real filehandle like +C<FH>, not an indirect one like C<$fh>. To set the default output handle +to something other than STDOUT, use the select operation. + +The current value of C<$,> (if any) is printed between each LIST item. The +current value of C<$\> (if any) is printed after the entire LIST has been +printed. Because print takes a LIST, anything in the LIST is evaluated in +list context, including any subroutines whose return lists you pass to +C<print>. Be careful not to follow the print keyword with a left +parenthesis unless you want the corresponding right parenthesis to +terminate the arguments to the print; put parentheses around all arguments +(or interpose a C<+>, but that doesn't look as good). + +If you're storing handles in an array or hash, or in general whenever +you're using any expression more complex than a bareword handle or a plain, +unsubscripted scalar variable to retrieve it, you will have to use a block +returning the filehandle value instead, in which case the LIST may not be +omitted: + + print { $files[$i] } "stuff\n"; + print { $OK ? STDOUT : STDERR } "stuff\n"; + +Printing to a closed pipe or socket will generate a SIGPIPE signal. See +L<perlipc> for more on signal handling. + +=item printf FILEHANDLE FORMAT, LIST +X<printf> + +=item printf FILEHANDLE + +=item printf FORMAT, LIST + +=item printf + +Equivalent to C<print FILEHANDLE sprintf(FORMAT, LIST)>, except that C<$\> +(the output record separator) is not appended. The first argument of the +list will be interpreted as the C<printf> format. See +L<sprintf|/sprintf FORMAT, LIST> for an +explanation of the format argument. If you omit the LIST, C<$_> is used; +to use FILEHANDLE without a LIST, you must use a real filehandle like +C<FH>, not an indirect one like C<$fh>. If C<use locale> is in effect and +POSIX::setlocale() has been called, the character used for the decimal +separator in formatted floating-point numbers is affected by the LC_NUMERIC +locale setting. See L<perllocale> and L<POSIX>. + +Don't fall into the trap of using a C<printf> when a simple +C<print> would do. The C<print> is more efficient and less +error prone. + +=item prototype FUNCTION +X<prototype> + +Returns the prototype of a function as a string (or C<undef> if the +function has no prototype). FUNCTION is a reference to, or the name of, +the function whose prototype you want to retrieve. + +If FUNCTION is a string starting with C<CORE::>, the rest is taken as a +name for a Perl builtin. If the builtin is not I<overridable> (such as +C<qw//>) or if its arguments cannot be adequately expressed by a prototype +(such as C<system>), prototype() returns C<undef>, because the builtin +does not really behave like a Perl function. Otherwise, the string +describing the equivalent prototype is returned. + +=item push ARRAY,LIST +X<push> X<stack> + +=item push EXPR,LIST + +Treats ARRAY as a stack by appending the values of LIST to the end of +ARRAY. The length of ARRAY increases by the length of LIST. Has the same +effect as + + for $value (LIST) { + $ARRAY[++$#ARRAY] = $value; + } + +but is more efficient. Returns the number of elements in the array following +the completed C<push>. + +Starting with Perl 5.14, C<push> can take a scalar EXPR, which must hold a +reference to an unblessed array. The argument will be dereferenced +automatically. This aspect of C<push> is considered highly experimental. +The exact behaviour may change in a future version of Perl. + +=item q/STRING/ + +=item qq/STRING/ + +=item qx/STRING/ + +=item qw/STRING/ + +Generalized quotes. See L<perlop/"Quote-Like Operators">. + +=item qr/STRING/ + +Regexp-like quote. See L<perlop/"Regexp Quote-Like Operators">. + +=item quotemeta EXPR +X<quotemeta> X<metacharacter> + +=item quotemeta + +Returns the value of EXPR with all non-"word" +characters backslashed. (That is, all characters not matching +C</[A-Za-z_0-9]/> will be preceded by a backslash in the +returned string, regardless of any locale settings.) +This is the internal function implementing +the C<\Q> escape in double-quoted strings. + +If EXPR is omitted, uses C<$_>. + +quotemeta (and C<\Q> ... C<\E>) are useful when interpolating strings into +regular expressions, because by default an interpolated variable will be +considered a mini-regular expression. For example: + + my $sentence = 'The quick brown fox jumped over the lazy dog'; + my $substring = 'quick.*?fox'; + $sentence =~ s{$substring}{big bad wolf}; + +Will cause C<$sentence> to become C<'The big bad wolf jumped over...'>. + +On the other hand: + + my $sentence = 'The quick brown fox jumped over the lazy dog'; + my $substring = 'quick.*?fox'; + $sentence =~ s{\Q$substring\E}{big bad wolf}; + +Or: + + my $sentence = 'The quick brown fox jumped over the lazy dog'; + my $substring = 'quick.*?fox'; + my $quoted_substring = quotemeta($substring); + $sentence =~ s{$quoted_substring}{big bad wolf}; + +Will both leave the sentence as is. Normally, when accepting literal string +input from the user, quotemeta() or C<\Q> must be used. + +In Perl 5.14, all characters whose code points are above 127 are not +quoted in UTF8-encoded strings, but all are quoted in UTF-8 strings. +It is planned to change this behavior in 5.16, but the exact rules +haven't been determined yet. + +=item rand EXPR +X<rand> X<random> + +=item rand + +Returns a random fractional number greater than or equal to C<0> and less +than the value of EXPR. (EXPR should be positive.) If EXPR is +omitted, the value C<1> is used. Currently EXPR with the value C<0> is +also special-cased as C<1> (this was undocumented before Perl 5.8.0 +and is subject to change in future versions of Perl). Automatically calls +C<srand> unless C<srand> has already been called. See also C<srand>. + +Apply C<int()> to the value returned by C<rand()> if you want random +integers instead of random fractional numbers. For example, + + int(rand(10)) + +returns a random integer between C<0> and C<9>, inclusive. + +(Note: If your rand function consistently returns numbers that are too +large or too small, then your version of Perl was probably compiled +with the wrong number of RANDBITS.) + +B<C<rand()> is not cryptographically secure. You should not rely +on it in security-sensitive situations.> As of this writing, a +number of third-party CPAN modules offer random number generators +intended by their authors to be cryptographically secure, +including: L<Data::Entropy>, L<Crypt::Random>, L<Math::Random::Secure>, +and L<Math::TrulyRandom>. + +=item read FILEHANDLE,SCALAR,LENGTH,OFFSET +X<read> X<file, read> + +=item read FILEHANDLE,SCALAR,LENGTH + +Attempts to read LENGTH I<characters> of data into variable SCALAR +from the specified FILEHANDLE. Returns the number of characters +actually read, C<0> at end of file, or undef if there was an error (in +the latter case C<$!> is also set). SCALAR will be grown or shrunk +so that the last character actually read is the last character of the +scalar after the read. + +An OFFSET may be specified to place the read data at some place in the +string other than the beginning. A negative OFFSET specifies +placement at that many characters counting backwards from the end of +the string. A positive OFFSET greater than the length of SCALAR +results in the string being padded to the required size with C<"\0"> +bytes before the result of the read is appended. + +The call is implemented in terms of either Perl's or your system's native +fread(3) library function. To get a true read(2) system call, see +L<sysread|/sysread FILEHANDLE,SCALAR,LENGTH,OFFSET>. + +Note the I<characters>: depending on the status of the filehandle, +either (8-bit) bytes or characters are read. By default, all +filehandles operate on bytes, but for example if the filehandle has +been opened with the C<:utf8> I/O layer (see L</open>, and the C<open> +pragma, L<open>), the I/O will operate on UTF8-encoded Unicode +characters, not bytes. Similarly for the C<:encoding> pragma: +in that case pretty much any characters can be read. + +=item readdir DIRHANDLE +X<readdir> + +Returns the next directory entry for a directory opened by C<opendir>. +If used in list context, returns all the rest of the entries in the +directory. If there are no more entries, returns the undefined value in +scalar context and the empty list in list context. + +If you're planning to filetest the return values out of a C<readdir>, you'd +better prepend the directory in question. Otherwise, because we didn't +C<chdir> there, it would have been testing the wrong file. + + opendir(my $dh, $some_dir) || die "can't opendir $some_dir: $!"; + @dots = grep { /^\./ && -f "$some_dir/$_" } readdir($dh); + closedir $dh; + +As of Perl 5.11.2 you can use a bare C<readdir> in a C<while> loop, +which will set C<$_> on every iteration. + + opendir(my $dh, $some_dir) || die; + while(readdir $dh) { + print "$some_dir/$_\n"; + } + closedir $dh; + +=item readline EXPR + +=item readline +X<readline> X<gets> X<fgets> + +Reads from the filehandle whose typeglob is contained in EXPR (or from +C<*ARGV> if EXPR is not provided). In scalar context, each call reads and +returns the next line until end-of-file is reached, whereupon the +subsequent call returns C<undef>. In list context, reads until end-of-file +is reached and returns a list of lines. Note that the notion of "line" +used here is whatever you may have defined with C<$/> or +C<$INPUT_RECORD_SEPARATOR>). See L<perlvar/"$/">. + +When C<$/> is set to C<undef>, when C<readline> is in scalar +context (i.e., file slurp mode), and when an empty file is read, it +returns C<''> the first time, followed by C<undef> subsequently. + +This is the internal function implementing the C<< <EXPR> >> +operator, but you can use it directly. The C<< <EXPR> >> +operator is discussed in more detail in L<perlop/"I/O Operators">. + + $line = <STDIN>; + $line = readline(*STDIN); # same thing + +If C<readline> encounters an operating system error, C<$!> will be set +with the corresponding error message. It can be helpful to check +C<$!> when you are reading from filehandles you don't trust, such as a +tty or a socket. The following example uses the operator form of +C<readline> and dies if the result is not defined. + + while ( ! eof($fh) ) { + defined( $_ = <$fh> ) or die "readline failed: $!"; + ... + } + +Note that you have can't handle C<readline> errors that way with the +C<ARGV> filehandle. In that case, you have to open each element of +C<@ARGV> yourself since C<eof> handles C<ARGV> differently. + + foreach my $arg (@ARGV) { + open(my $fh, $arg) or warn "Can't open $arg: $!"; + + while ( ! eof($fh) ) { + defined( $_ = <$fh> ) + or die "readline failed for $arg: $!"; + ... + } + } + +=item readlink EXPR +X<readlink> + +=item readlink + +Returns the value of a symbolic link, if symbolic links are +implemented. If not, raises an exception. If there is a system +error, returns the undefined value and sets C<$!> (errno). If EXPR is +omitted, uses C<$_>. + +Portability issues: L<perlport/readlink>. + +=item readpipe EXPR + +=item readpipe +X<readpipe> + +EXPR is executed as a system command. +The collected standard output of the command is returned. +In scalar context, it comes back as a single (potentially +multi-line) string. In list context, returns a list of lines +(however you've defined lines with C<$/> or C<$INPUT_RECORD_SEPARATOR>). +This is the internal function implementing the C<qx/EXPR/> +operator, but you can use it directly. The C<qx/EXPR/> +operator is discussed in more detail in L<perlop/"I/O Operators">. +If EXPR is omitted, uses C<$_>. + +=item recv SOCKET,SCALAR,LENGTH,FLAGS +X<recv> + +Receives a message on a socket. Attempts to receive LENGTH characters +of data into variable SCALAR from the specified SOCKET filehandle. +SCALAR will be grown or shrunk to the length actually read. Takes the +same flags as the system call of the same name. Returns the address +of the sender if SOCKET's protocol supports this; returns an empty +string otherwise. If there's an error, returns the undefined value. +This call is actually implemented in terms of recvfrom(2) system call. +See L<perlipc/"UDP: Message Passing"> for examples. + +Note the I<characters>: depending on the status of the socket, either +(8-bit) bytes or characters are received. By default all sockets +operate on bytes, but for example if the socket has been changed using +binmode() to operate with the C<:encoding(utf8)> I/O layer (see the +C<open> pragma, L<open>), the I/O will operate on UTF8-encoded Unicode +characters, not bytes. Similarly for the C<:encoding> pragma: in that +case pretty much any characters can be read. + +=item redo LABEL +X<redo> + +=item redo + +The C<redo> command restarts the loop block without evaluating the +conditional again. The C<continue> block, if any, is not executed. If +the LABEL is omitted, the command refers to the innermost enclosing +loop. Programs that want to lie to themselves about what was just input +normally use this command: + + # a simpleminded Pascal comment stripper + # (warning: assumes no { or } in strings) + LINE: while (<STDIN>) { + while (s|({.*}.*){.*}|$1 |) {} + s|{.*}| |; + if (s|{.*| |) { + $front = $_; + while (<STDIN>) { + if (/}/) { # end of comment? + s|^|$front\{|; + redo LINE; + } + } + } + print; + } + +C<redo> cannot be used to retry a block that returns a value such as +C<eval {}>, C<sub {}>, or C<do {}>, and should not be used to exit +a grep() or map() operation. + +Note that a block by itself is semantically identical to a loop +that executes once. Thus C<redo> inside such a block will effectively +turn it into a looping construct. + +See also L</continue> for an illustration of how C<last>, C<next>, and +C<redo> work. + +=item ref EXPR +X<ref> X<reference> + +=item ref + +Returns a non-empty string if EXPR is a reference, the empty +string otherwise. If EXPR +is not specified, C<$_> will be used. The value returned depends on the +type of thing the reference is a reference to. +Builtin types include: + + SCALAR + ARRAY + HASH + CODE + REF + GLOB + LVALUE + FORMAT + IO + VSTRING + Regexp + +If the referenced object has been blessed into a package, then that package +name is returned instead. You can think of C<ref> as a C<typeof> operator. + + if (ref($r) eq "HASH") { + print "r is a reference to a hash.\n"; + } + unless (ref($r)) { + print "r is not a reference at all.\n"; + } + +The return value C<LVALUE> indicates a reference to an lvalue that is not +a variable. You get this from taking the reference of function calls like +C<pos()> or C<substr()>. C<VSTRING> is returned if the reference points +to a L<version string|perldata/"Version Strings">. + +The result C<Regexp> indicates that the argument is a regular expression +resulting from C<qr//>. + +See also L<perlref>. + +=item rename OLDNAME,NEWNAME +X<rename> X<move> X<mv> X<ren> + +Changes the name of a file; an existing file NEWNAME will be +clobbered. Returns true for success, false otherwise. + +Behavior of this function varies wildly depending on your system +implementation. For example, it will usually not work across file system +boundaries, even though the system I<mv> command sometimes compensates +for this. Other restrictions include whether it works on directories, +open files, or pre-existing files. Check L<perlport> and either the +rename(2) manpage or equivalent system documentation for details. + +For a platform independent C<move> function look at the L<File::Copy> +module. + +Portability issues: L<perlport/rename>. + +=item require VERSION +X<require> + +=item require EXPR + +=item require + +Demands a version of Perl specified by VERSION, or demands some semantics +specified by EXPR or by C<$_> if EXPR is not supplied. + +VERSION may be either a numeric argument such as 5.006, which will be +compared to C<$]>, or a literal of the form v5.6.1, which will be compared +to C<$^V> (aka $PERL_VERSION). An exception is raised if +VERSION is greater than the version of the current Perl interpreter. +Compare with L</use>, which can do a similar check at compile time. + +Specifying VERSION as a literal of the form v5.6.1 should generally be +avoided, because it leads to misleading error messages under earlier +versions of Perl that do not support this syntax. The equivalent numeric +version should be used instead. + + require v5.6.1; # run time version check + require 5.6.1; # ditto + require 5.006_001; # ditto; preferred for backwards compatibility + +Otherwise, C<require> demands that a library file be included if it +hasn't already been included. The file is included via the do-FILE +mechanism, which is essentially just a variety of C<eval> with the +caveat that lexical variables in the invoking script will be invisible +to the included code. Has semantics similar to the following subroutine: + + sub require { + my ($filename) = @_; + if (exists $INC{$filename}) { + return 1 if $INC{$filename}; + die "Compilation failed in require"; + } + my ($realfilename,$result); + ITER: { + foreach $prefix (@INC) { + $realfilename = "$prefix/$filename"; + if (-f $realfilename) { + $INC{$filename} = $realfilename; + $result = do $realfilename; + last ITER; + } + } + die "Can't find $filename in \@INC"; + } + if ($@) { + $INC{$filename} = undef; + die $@; + } elsif (!$result) { + delete $INC{$filename}; + die "$filename did not return true value"; + } else { + return $result; + } + } + +Note that the file will not be included twice under the same specified +name. + +The file must return true as the last statement to indicate +successful execution of any initialization code, so it's customary to +end such a file with C<1;> unless you're sure it'll return true +otherwise. But it's better just to put the C<1;>, in case you add more +statements. + +If EXPR is a bareword, the require assumes a "F<.pm>" extension and +replaces "F<::>" with "F</>" in the filename for you, +to make it easy to load standard modules. This form of loading of +modules does not risk altering your namespace. + +In other words, if you try this: + + require Foo::Bar; # a splendid bareword + +The require function will actually look for the "F<Foo/Bar.pm>" file in the +directories specified in the C<@INC> array. + +But if you try this: + + $class = 'Foo::Bar'; + require $class; # $class is not a bareword + #or + require "Foo::Bar"; # not a bareword because of the "" + +The require function will look for the "F<Foo::Bar>" file in the @INC array and +will complain about not finding "F<Foo::Bar>" there. In this case you can do: + + eval "require $class"; + +Now that you understand how C<require> looks for files with a +bareword argument, there is a little extra functionality going on behind +the scenes. Before C<require> looks for a "F<.pm>" extension, it will +first look for a similar filename with a "F<.pmc>" extension. If this file +is found, it will be loaded in place of any file ending in a "F<.pm>" +extension. + +You can also insert hooks into the import facility by putting Perl code +directly into the @INC array. There are three forms of hooks: subroutine +references, array references, and blessed objects. + +Subroutine references are the simplest case. When the inclusion system +walks through @INC and encounters a subroutine, this subroutine gets +called with two parameters, the first a reference to itself, and the +second the name of the file to be included (e.g., "F<Foo/Bar.pm>"). The +subroutine should return either nothing or else a list of up to three +values in the following order: + +=over + +=item 1 + +A filehandle, from which the file will be read. + +=item 2 + +A reference to a subroutine. If there is no filehandle (previous item), +then this subroutine is expected to generate one line of source code per +call, writing the line into C<$_> and returning 1, then finally at end of +file returning 0. If there is a filehandle, then the subroutine will be +called to act as a simple source filter, with the line as read in C<$_>. +Again, return 1 for each valid line, and 0 after all lines have been +returned. + +=item 3 + +Optional state for the subroutine. The state is passed in as C<$_[1]>. A +reference to the subroutine itself is passed in as C<$_[0]>. + +=back + +If an empty list, C<undef>, or nothing that matches the first 3 values above +is returned, then C<require> looks at the remaining elements of @INC. +Note that this filehandle must be a real filehandle (strictly a typeglob +or reference to a typeglob, whether blessed or unblessed); tied filehandles +will be ignored and processing will stop there. + +If the hook is an array reference, its first element must be a subroutine +reference. This subroutine is called as above, but the first parameter is +the array reference. This lets you indirectly pass arguments to +the subroutine. + +In other words, you can write: + + push @INC, \&my_sub; + sub my_sub { + my ($coderef, $filename) = @_; # $coderef is \&my_sub + ... + } + +or: + + push @INC, [ \&my_sub, $x, $y, ... ]; + sub my_sub { + my ($arrayref, $filename) = @_; + # Retrieve $x, $y, ... + my @parameters = @$arrayref[1..$#$arrayref]; + ... + } + +If the hook is an object, it must provide an INC method that will be +called as above, the first parameter being the object itself. (Note that +you must fully qualify the sub's name, as unqualified C<INC> is always forced +into package C<main>.) Here is a typical code layout: + + # In Foo.pm + package Foo; + sub new { ... } + sub Foo::INC { + my ($self, $filename) = @_; + ... + } + + # In the main program + push @INC, Foo->new(...); + +These hooks are also permitted to set the %INC entry +corresponding to the files they have loaded. See L<perlvar/%INC>. + +For a yet-more-powerful import facility, see L</use> and L<perlmod>. + +=item reset EXPR +X<reset> + +=item reset + +Generally used in a C<continue> block at the end of a loop to clear +variables and reset C<??> searches so that they work again. The +expression is interpreted as a list of single characters (hyphens +allowed for ranges). All variables and arrays beginning with one of +those letters are reset to their pristine state. If the expression is +omitted, one-match searches (C<?pattern?>) are reset to match again. +Only resets variables or searches in the current package. Always returns +1. Examples: + + reset 'X'; # reset all X variables + reset 'a-z'; # reset lower case variables + reset; # just reset ?one-time? searches + +Resetting C<"A-Z"> is not recommended because you'll wipe out your +C<@ARGV> and C<@INC> arrays and your C<%ENV> hash. Resets only package +variables; lexical variables are unaffected, but they clean themselves +up on scope exit anyway, so you'll probably want to use them instead. +See L</my>. + +=item return EXPR +X<return> + +=item return + +Returns from a subroutine, C<eval>, or C<do FILE> with the value +given in EXPR. Evaluation of EXPR may be in list, scalar, or void +context, depending on how the return value will be used, and the context +may vary from one execution to the next (see L</wantarray>). If no EXPR +is given, returns an empty list in list context, the undefined value in +scalar context, and (of course) nothing at all in void context. + +(In the absence of an explicit C<return>, a subroutine, eval, +or do FILE automatically returns the value of the last expression +evaluated.) + +=item reverse LIST +X<reverse> X<rev> X<invert> + +In list context, returns a list value consisting of the elements +of LIST in the opposite order. In scalar context, concatenates the +elements of LIST and returns a string value with all characters +in the opposite order. + + print join(", ", reverse "world", "Hello"); # Hello, world + + print scalar reverse "dlrow ,", "olleH"; # Hello, world + +Used without arguments in scalar context, reverse() reverses C<$_>. + + $_ = "dlrow ,olleH"; + print reverse; # No output, list context + print scalar reverse; # Hello, world + +Note that reversing an array to itself (as in C<@a = reverse @a>) will +preserve non-existent elements whenever possible, i.e., for non magical +arrays or tied arrays with C<EXISTS> and C<DELETE> methods. + +This operator is also handy for inverting a hash, although there are some +caveats. If a value is duplicated in the original hash, only one of those +can be represented as a key in the inverted hash. Also, this has to +unwind one hash and build a whole new one, which may take some time +on a large hash, such as from a DBM file. + + %by_name = reverse %by_address; # Invert the hash + +=item rewinddir DIRHANDLE +X<rewinddir> + +Sets the current position to the beginning of the directory for the +C<readdir> routine on DIRHANDLE. + +Portability issues: L<perlport/rewinddir>. + +=item rindex STR,SUBSTR,POSITION +X<rindex> + +=item rindex STR,SUBSTR + +Works just like index() except that it returns the position of the I<last> +occurrence of SUBSTR in STR. If POSITION is specified, returns the +last occurrence beginning at or before that position. + +=item rmdir FILENAME +X<rmdir> X<rd> X<directory, remove> + +=item rmdir + +Deletes the directory specified by FILENAME if that directory is +empty. If it succeeds it returns true; otherwise it returns false and +sets C<$!> (errno). If FILENAME is omitted, uses C<$_>. + +To remove a directory tree recursively (C<rm -rf> on Unix) look at +the C<rmtree> function of the L<File::Path> module. + +=item s/// + +The substitution operator. See L<perlop/"Regexp Quote-Like Operators">. + +=item say FILEHANDLE LIST +X<say> + +=item say FILEHANDLE + +=item say LIST + +=item say + +Just like C<print>, but implicitly appends a newline. C<say LIST> is +simply an abbreviation for C<{ local $\ = "\n"; print LIST }>. To use +FILEHANDLE without a LIST to print the contents of C<$_> to it, you must +use a real filehandle like C<FH>, not an indirect one like C<$fh>. + +This keyword is available only when the C<"say"> feature +is enabled, or when prefixed with C<CORE::>; see +L<feature>. Alternately, include a C<use v5.10> or later to the current +scope. + +=item scalar EXPR +X<scalar> X<context> + +Forces EXPR to be interpreted in scalar context and returns the value +of EXPR. + + @counts = ( scalar @a, scalar @b, scalar @c ); + +There is no equivalent operator to force an expression to +be interpolated in list context because in practice, this is never +needed. If you really wanted to do so, however, you could use +the construction C<@{[ (some expression) ]}>, but usually a simple +C<(some expression)> suffices. + +Because C<scalar> is a unary operator, if you accidentally use a +parenthesized list for the EXPR, this behaves as a scalar comma expression, +evaluating all but the last element in void context and returning the final +element evaluated in scalar context. This is seldom what you want. + +The following single statement: + + print uc(scalar(&foo,$bar)),$baz; + +is the moral equivalent of these two: + + &foo; + print(uc($bar),$baz); + +See L<perlop> for more details on unary operators and the comma operator. + +=item seek FILEHANDLE,POSITION,WHENCE +X<seek> X<fseek> X<filehandle, position> + +Sets FILEHANDLE's position, just like the C<fseek> call of C<stdio>. +FILEHANDLE may be an expression whose value gives the name of the +filehandle. The values for WHENCE are C<0> to set the new position +I<in bytes> to POSITION; C<1> to set it to the current position plus +POSITION; and C<2> to set it to EOF plus POSITION, typically +negative. For WHENCE you may use the constants C<SEEK_SET>, +C<SEEK_CUR>, and C<SEEK_END> (start of the file, current position, end +of the file) from the L<Fcntl> module. Returns C<1> on success, false +otherwise. + +Note the I<in bytes>: even if the filehandle has been set to +operate on characters (for example by using the C<:encoding(utf8)> open +layer), tell() will return byte offsets, not character offsets +(because implementing that would render seek() and tell() rather slow). + +If you want to position the file for C<sysread> or C<syswrite>, don't use +C<seek>, because buffering makes its effect on the file's read-write position +unpredictable and non-portable. Use C<sysseek> instead. + +Due to the rules and rigors of ANSI C, on some systems you have to do a +seek whenever you switch between reading and writing. Amongst other +things, this may have the effect of calling stdio's clearerr(3). +A WHENCE of C<1> (C<SEEK_CUR>) is useful for not moving the file position: + + seek(TEST,0,1); + +This is also useful for applications emulating C<tail -f>. Once you hit +EOF on your read and then sleep for a while, you (probably) have to stick in a +dummy seek() to reset things. The C<seek> doesn't change the position, +but it I<does> clear the end-of-file condition on the handle, so that the +next C<< <FILE> >> makes Perl try again to read something. (We hope.) + +If that doesn't work (some I/O implementations are particularly +cantankerous), you might need something like this: + + for (;;) { + for ($curpos = tell(FILE); $_ = <FILE>; + $curpos = tell(FILE)) { + # search for some stuff and put it into files + } + sleep($for_a_while); + seek(FILE, $curpos, 0); + } + +=item seekdir DIRHANDLE,POS +X<seekdir> + +Sets the current position for the C<readdir> routine on DIRHANDLE. POS +must be a value returned by C<telldir>. C<seekdir> also has the same caveats +about possible directory compaction as the corresponding system library +routine. + +=item select FILEHANDLE +X<select> X<filehandle, default> + +=item select + +Returns the currently selected filehandle. If FILEHANDLE is supplied, +sets the new current default filehandle for output. This has two +effects: first, a C<write> or a C<print> without a filehandle +default to this FILEHANDLE. Second, references to variables related to +output will refer to this output channel. + +For example, to set the top-of-form format for more than one +output channel, you might do the following: + + select(REPORT1); + $^ = 'report1_top'; + select(REPORT2); + $^ = 'report2_top'; + +FILEHANDLE may be an expression whose value gives the name of the +actual filehandle. Thus: + + $oldfh = select(STDERR); $| = 1; select($oldfh); + +Some programmers may prefer to think of filehandles as objects with +methods, preferring to write the last example as: + + use IO::Handle; + STDERR->autoflush(1); + +Portability issues: L<perlport/select>. + +=item select RBITS,WBITS,EBITS,TIMEOUT +X<select> + +This calls the select(2) syscall with the bit masks specified, which +can be constructed using C<fileno> and C<vec>, along these lines: + + $rin = $win = $ein = ''; + vec($rin, fileno(STDIN), 1) = 1; + vec($win, fileno(STDOUT), 1) = 1; + $ein = $rin | $win; + +If you want to select on many filehandles, you may wish to write a +subroutine like this: + + sub fhbits { + my @fhlist = @_; + my $bits = ""; + for my $fh (@fhlist) { + vec($bits, fileno($fh), 1) = 1; + } + return $bits; + } + $rin = fhbits(*STDIN, *TTY, *MYSOCK); + +The usual idiom is: + + ($nfound,$timeleft) = + select($rout=$rin, $wout=$win, $eout=$ein, $timeout); + +or to block until something becomes ready just do this + + $nfound = select($rout=$rin, $wout=$win, $eout=$ein, undef); + +Most systems do not bother to return anything useful in $timeleft, so +calling select() in scalar context just returns $nfound. + +Any of the bit masks can also be undef. The timeout, if specified, is +in seconds, which may be fractional. Note: not all implementations are +capable of returning the $timeleft. If not, they always return +$timeleft equal to the supplied $timeout. + +You can effect a sleep of 250 milliseconds this way: + + select(undef, undef, undef, 0.25); + +Note that whether C<select> gets restarted after signals (say, SIGALRM) +is implementation-dependent. See also L<perlport> for notes on the +portability of C<select>. + +On error, C<select> behaves just like select(2): it returns +-1 and sets C<$!>. + +On some Unixes, select(2) may report a socket file descriptor as "ready for +reading" even when no data is available, and thus any subsequent C<read> +would block. This can be avoided if you always use O_NONBLOCK on the +socket. See select(2) and fcntl(2) for further details. + +The standard C<IO::Select> module provides a user-friendlier interface +to C<select>, mostly because it does all the bit-mask work for you. + +B<WARNING>: One should not attempt to mix buffered I/O (like C<read> +or <FH>) with C<select>, except as permitted by POSIX, and even +then only on POSIX systems. You have to use C<sysread> instead. + +Portability issues: L<perlport/select>. + +=item semctl ID,SEMNUM,CMD,ARG +X<semctl> + +Calls the System V IPC function semctl(2). You'll probably have to say + + use IPC::SysV; + +first to get the correct constant definitions. If CMD is IPC_STAT or +GETALL, then ARG must be a variable that will hold the returned +semid_ds structure or semaphore value array. Returns like C<ioctl>: +the undefined value for error, "C<0 but true>" for zero, or the actual +return value otherwise. The ARG must consist of a vector of native +short integers, which may be created with C<pack("s!",(0)x$nsem)>. +See also L<perlipc/"SysV IPC">, C<IPC::SysV>, C<IPC::Semaphore> +documentation. + +Portability issues: L<perlport/semctl>. + +=item semget KEY,NSEMS,FLAGS +X<semget> + +Calls the System V IPC function semget(2). Returns the semaphore id, or +the undefined value on error. See also +L<perlipc/"SysV IPC">, C<IPC::SysV>, C<IPC::SysV::Semaphore> +documentation. + +Portability issues: L<perlport/semget>. + +=item semop KEY,OPSTRING +X<semop> + +Calls the System V IPC function semop(2) for semaphore operations +such as signalling and waiting. OPSTRING must be a packed array of +semop structures. Each semop structure can be generated with +C<pack("s!3", $semnum, $semop, $semflag)>. The length of OPSTRING +implies the number of semaphore operations. Returns true if +successful, false on error. As an example, the +following code waits on semaphore $semnum of semaphore id $semid: + + $semop = pack("s!3", $semnum, -1, 0); + die "Semaphore trouble: $!\n" unless semop($semid, $semop); + +To signal the semaphore, replace C<-1> with C<1>. See also +L<perlipc/"SysV IPC">, C<IPC::SysV>, and C<IPC::SysV::Semaphore> +documentation. + +Portability issues: L<perlport/semop>. + +=item send SOCKET,MSG,FLAGS,TO +X<send> + +=item send SOCKET,MSG,FLAGS + +Sends a message on a socket. Attempts to send the scalar MSG to the SOCKET +filehandle. Takes the same flags as the system call of the same name. On +unconnected sockets, you must specify a destination to I<send to>, in which +case it does a sendto(2) syscall. Returns the number of characters sent, +or the undefined value on error. The sendmsg(2) syscall is currently +unimplemented. See L<perlipc/"UDP: Message Passing"> for examples. + +Note the I<characters>: depending on the status of the socket, either +(8-bit) bytes or characters are sent. By default all sockets operate +on bytes, but for example if the socket has been changed using +binmode() to operate with the C<:encoding(utf8)> I/O layer (see +L</open>, or the C<open> pragma, L<open>), the I/O will operate on UTF-8 +encoded Unicode characters, not bytes. Similarly for the C<:encoding> +pragma: in that case pretty much any characters can be sent. + +=item setpgrp PID,PGRP +X<setpgrp> X<group> + +Sets the current process group for the specified PID, C<0> for the current +process. Raises an exception when used on a machine that doesn't +implement POSIX setpgid(2) or BSD setpgrp(2). If the arguments are omitted, +it defaults to C<0,0>. Note that the BSD 4.2 version of C<setpgrp> does not +accept any arguments, so only C<setpgrp(0,0)> is portable. See also +C<POSIX::setsid()>. + +Portability issues: L<perlport/setpgrp>. + +=item setpriority WHICH,WHO,PRIORITY +X<setpriority> X<priority> X<nice> X<renice> + +Sets the current priority for a process, a process group, or a user. +(See setpriority(2).) Raises an exception when used on a machine +that doesn't implement setpriority(2). + +Portability issues: L<perlport/setpriority>. + +=item setsockopt SOCKET,LEVEL,OPTNAME,OPTVAL +X<setsockopt> + +Sets the socket option requested. Returns C<undef> on error. +Use integer constants provided by the C<Socket> module for +LEVEL and OPNAME. Values for LEVEL can also be obtained from +getprotobyname. OPTVAL might either be a packed string or an integer. +An integer OPTVAL is shorthand for pack("i", OPTVAL). + +An example disabling Nagle's algorithm on a socket: + + use Socket qw(IPPROTO_TCP TCP_NODELAY); + setsockopt($socket, IPPROTO_TCP, TCP_NODELAY, 1); + +Portability issues: L<perlport/setsockopt>. + +=item shift ARRAY +X<shift> + +=item shift EXPR + +=item shift + +Shifts the first value of the array off and returns it, shortening the +array by 1 and moving everything down. If there are no elements in the +array, returns the undefined value. If ARRAY is omitted, shifts the +C<@_> array within the lexical scope of subroutines and formats, and the +C<@ARGV> array outside a subroutine and also within the lexical scopes +established by the C<eval STRING>, C<BEGIN {}>, C<INIT {}>, C<CHECK {}>, +C<UNITCHECK {}>, and C<END {}> constructs. + +Starting with Perl 5.14, C<shift> can take a scalar EXPR, which must hold a +reference to an unblessed array. The argument will be dereferenced +automatically. This aspect of C<shift> is considered highly experimental. +The exact behaviour may change in a future version of Perl. + +See also C<unshift>, C<push>, and C<pop>. C<shift> and C<unshift> do the +same thing to the left end of an array that C<pop> and C<push> do to the +right end. + +=item shmctl ID,CMD,ARG +X<shmctl> + +Calls the System V IPC function shmctl. You'll probably have to say + + use IPC::SysV; + +first to get the correct constant definitions. If CMD is C<IPC_STAT>, +then ARG must be a variable that will hold the returned C<shmid_ds> +structure. Returns like ioctl: C<undef> for error; "C<0> but +true" for zero; and the actual return value otherwise. +See also L<perlipc/"SysV IPC"> and C<IPC::SysV> documentation. + +Portability issues: L<perlport/shmctl>. + +=item shmget KEY,SIZE,FLAGS +X<shmget> + +Calls the System V IPC function shmget. Returns the shared memory +segment id, or C<undef> on error. +See also L<perlipc/"SysV IPC"> and C<IPC::SysV> documentation. + +Portability issues: L<perlport/shmget>. + +=item shmread ID,VAR,POS,SIZE +X<shmread> +X<shmwrite> + +=item shmwrite ID,STRING,POS,SIZE + +Reads or writes the System V shared memory segment ID starting at +position POS for size SIZE by attaching to it, copying in/out, and +detaching from it. When reading, VAR must be a variable that will +hold the data read. When writing, if STRING is too long, only SIZE +bytes are used; if STRING is too short, nulls are written to fill out +SIZE bytes. Return true if successful, false on error. +shmread() taints the variable. See also L<perlipc/"SysV IPC">, +C<IPC::SysV>, and the C<IPC::Shareable> module from CPAN. + +Portability issues: L<perlport/shmread> and L<perlport/shmwrite>. + +=item shutdown SOCKET,HOW +X<shutdown> + +Shuts down a socket connection in the manner indicated by HOW, which +has the same interpretation as in the syscall of the same name. + + shutdown(SOCKET, 0); # I/we have stopped reading data + shutdown(SOCKET, 1); # I/we have stopped writing data + shutdown(SOCKET, 2); # I/we have stopped using this socket + +This is useful with sockets when you want to tell the other +side you're done writing but not done reading, or vice versa. +It's also a more insistent form of close because it also +disables the file descriptor in any forked copies in other +processes. + +Returns C<1> for success; on error, returns C<undef> if +the first argument is not a valid filehandle, or returns C<0> and sets +C<$!> for any other failure. + +=item sin EXPR +X<sin> X<sine> X<asin> X<arcsine> + +=item sin + +Returns the sine of EXPR (expressed in radians). If EXPR is omitted, +returns sine of C<$_>. + +For the inverse sine operation, you may use the C<Math::Trig::asin> +function, or use this relation: + + sub asin { atan2($_[0], sqrt(1 - $_[0] * $_[0])) } + +=item sleep EXPR +X<sleep> X<pause> + +=item sleep + +Causes the script to sleep for (integer) EXPR seconds, or forever if no +argument is given. Returns the integer number of seconds actually slept. + +May be interrupted if the process receives a signal such as C<SIGALRM>. + + eval { + local $SIG{ALARM} = sub { die "Alarm!\n" }; + sleep; + }; + die $@ unless $@ eq "Alarm!\n"; + +You probably cannot mix C<alarm> and C<sleep> calls, because C<sleep> +is often implemented using C<alarm>. + +On some older systems, it may sleep up to a full second less than what +you requested, depending on how it counts seconds. Most modern systems +always sleep the full amount. They may appear to sleep longer than that, +however, because your process might not be scheduled right away in a +busy multitasking system. + +For delays of finer granularity than one second, the Time::HiRes module +(from CPAN, and starting from Perl 5.8 part of the standard +distribution) provides usleep(). You may also use Perl's four-argument +version of select() leaving the first three arguments undefined, or you +might be able to use the C<syscall> interface to access setitimer(2) if +your system supports it. See L<perlfaq8> for details. + +See also the POSIX module's C<pause> function. + +=item socket SOCKET,DOMAIN,TYPE,PROTOCOL +X<socket> + +Opens a socket of the specified kind and attaches it to filehandle +SOCKET. DOMAIN, TYPE, and PROTOCOL are specified the same as for +the syscall of the same name. You should C<use Socket> first +to get the proper definitions imported. See the examples in +L<perlipc/"Sockets: Client/Server Communication">. + +On systems that support a close-on-exec flag on files, the flag will +be set for the newly opened file descriptor, as determined by the +value of $^F. See L<perlvar/$^F>. + +=item socketpair SOCKET1,SOCKET2,DOMAIN,TYPE,PROTOCOL +X<socketpair> + +Creates an unnamed pair of sockets in the specified domain, of the +specified type. DOMAIN, TYPE, and PROTOCOL are specified the same as +for the syscall of the same name. If unimplemented, raises an exception. +Returns true if successful. + +On systems that support a close-on-exec flag on files, the flag will +be set for the newly opened file descriptors, as determined by the value +of $^F. See L<perlvar/$^F>. + +Some systems defined C<pipe> in terms of C<socketpair>, in which a call +to C<pipe(Rdr, Wtr)> is essentially: + + use Socket; + socketpair(Rdr, Wtr, AF_UNIX, SOCK_STREAM, PF_UNSPEC); + shutdown(Rdr, 1); # no more writing for reader + shutdown(Wtr, 0); # no more reading for writer + +See L<perlipc> for an example of socketpair use. Perl 5.8 and later will +emulate socketpair using IP sockets to localhost if your system implements +sockets but not socketpair. + +Portability issues: L<perlport/socketpair>. + +=item sort SUBNAME LIST +X<sort> X<qsort> X<quicksort> X<mergesort> + +=item sort BLOCK LIST + +=item sort LIST + +In list context, this sorts the LIST and returns the sorted list value. +In scalar context, the behaviour of C<sort()> is undefined. + +If SUBNAME or BLOCK is omitted, C<sort>s in standard string comparison +order. If SUBNAME is specified, it gives the name of a subroutine +that returns an integer less than, equal to, or greater than C<0>, +depending on how the elements of the list are to be ordered. (The +C<< <=> >> and C<cmp> operators are extremely useful in such routines.) +SUBNAME may be a scalar variable name (unsubscripted), in which case +the value provides the name of (or a reference to) the actual +subroutine to use. In place of a SUBNAME, you can provide a BLOCK as +an anonymous, in-line sort subroutine. + +If the subroutine's prototype is C<($$)>, the elements to be compared are +passed by reference in C<@_>, as for a normal subroutine. This is slower +than unprototyped subroutines, where the elements to be compared are passed +into the subroutine as the package global variables $a and $b (see example +below). Note that in the latter case, it is usually highly counter-productive +to declare $a and $b as lexicals. + +If the subroutine is an XSUB, the elements to be compared are pushed on to +the stack, the way arguments are usually passed to XSUBs. $a and $b are +not set. + +The values to be compared are always passed by reference and should not +be modified. + +You also cannot exit out of the sort block or subroutine using any of the +loop control operators described in L<perlsyn> or with C<goto>. + +When C<use locale> is in effect, C<sort LIST> sorts LIST according to the +current collation locale. See L<perllocale>. + +sort() returns aliases into the original list, much as a for loop's index +variable aliases the list elements. That is, modifying an element of a +list returned by sort() (for example, in a C<foreach>, C<map> or C<grep>) +actually modifies the element in the original list. This is usually +something to be avoided when writing clear code. + +Perl 5.6 and earlier used a quicksort algorithm to implement sort. +That algorithm was not stable, so I<could> go quadratic. (A I<stable> sort +preserves the input order of elements that compare equal. Although +quicksort's run time is O(NlogN) when averaged over all arrays of +length N, the time can be O(N**2), I<quadratic> behavior, for some +inputs.) In 5.7, the quicksort implementation was replaced with +a stable mergesort algorithm whose worst-case behavior is O(NlogN). +But benchmarks indicated that for some inputs, on some platforms, +the original quicksort was faster. 5.8 has a sort pragma for +limited control of the sort. Its rather blunt control of the +underlying algorithm may not persist into future Perls, but the +ability to characterize the input or output in implementation +independent ways quite probably will. See L<the sort pragma|sort>. + +Examples: + + # sort lexically + @articles = sort @files; + + # same thing, but with explicit sort routine + @articles = sort {$a cmp $b} @files; + + # now case-insensitively + @articles = sort {uc($a) cmp uc($b)} @files; + + # same thing in reversed order + @articles = sort {$b cmp $a} @files; + + # sort numerically ascending + @articles = sort {$a <=> $b} @files; + + # sort numerically descending + @articles = sort {$b <=> $a} @files; + + # this sorts the %age hash by value instead of key + # using an in-line function + @eldest = sort { $age{$b} <=> $age{$a} } keys %age; + + # sort using explicit subroutine name + sub byage { + $age{$a} <=> $age{$b}; # presuming numeric + } + @sortedclass = sort byage @class; + + sub backwards { $b cmp $a } + @harry = qw(dog cat x Cain Abel); + @george = qw(gone chased yz Punished Axed); + print sort @harry; + # prints AbelCaincatdogx + print sort backwards @harry; + # prints xdogcatCainAbel + print sort @george, 'to', @harry; + # prints AbelAxedCainPunishedcatchaseddoggonetoxyz + + # inefficiently sort by descending numeric compare using + # the first integer after the first = sign, or the + # whole record case-insensitively otherwise + + my @new = sort { + ($b =~ /=(\d+)/)[0] <=> ($a =~ /=(\d+)/)[0] + || + uc($a) cmp uc($b) + } @old; + + # same thing, but much more efficiently; + # we'll build auxiliary indices instead + # for speed + my @nums = @caps = (); + for (@old) { + push @nums, ( /=(\d+)/ ? $1 : undef ); + push @caps, uc($_); + } + + my @new = @old[ sort { + $nums[$b] <=> $nums[$a] + || + $caps[$a] cmp $caps[$b] + } 0..$#old + ]; + + # same thing, but without any temps + @new = map { $_->[0] } + sort { $b->[1] <=> $a->[1] + || + $a->[2] cmp $b->[2] + } map { [$_, /=(\d+)/, uc($_)] } @old; + + # using a prototype allows you to use any comparison subroutine + # as a sort subroutine (including other package's subroutines) + package other; + sub backwards ($$) { $_[1] cmp $_[0]; } # $a and $b are not set here + + package main; + @new = sort other::backwards @old; + + # guarantee stability, regardless of algorithm + use sort 'stable'; + @new = sort { substr($a, 3, 5) cmp substr($b, 3, 5) } @old; + + # force use of mergesort (not portable outside Perl 5.8) + use sort '_mergesort'; # note discouraging _ + @new = sort { substr($a, 3, 5) cmp substr($b, 3, 5) } @old; + +Warning: syntactical care is required when sorting the list returned from +a function. If you want to sort the list returned by the function call +C<find_records(@key)>, you can use: + + @contact = sort { $a cmp $b } find_records @key; + @contact = sort +find_records(@key); + @contact = sort &find_records(@key); + @contact = sort(find_records(@key)); + +If instead you want to sort the array @key with the comparison routine +C<find_records()> then you can use: + + @contact = sort { find_records() } @key; + @contact = sort find_records(@key); + @contact = sort(find_records @key); + @contact = sort(find_records (@key)); + +If you're using strict, you I<must not> declare $a +and $b as lexicals. They are package globals. That means +that if you're in the C<main> package and type + + @articles = sort {$b <=> $a} @files; + +then C<$a> and C<$b> are C<$main::a> and C<$main::b> (or C<$::a> and C<$::b>), +but if you're in the C<FooPack> package, it's the same as typing + + @articles = sort {$FooPack::b <=> $FooPack::a} @files; + +The comparison function is required to behave. If it returns +inconsistent results (sometimes saying C<$x[1]> is less than C<$x[2]> and +sometimes saying the opposite, for example) the results are not +well-defined. + +Because C<< <=> >> returns C<undef> when either operand is C<NaN> +(not-a-number), be careful when sorting with a +comparison function like C<< $a <=> $b >> any lists that might contain a +C<NaN>. The following example takes advantage that C<NaN != NaN> to +eliminate any C<NaN>s from the input list. + + @result = sort { $a <=> $b } grep { $_ == $_ } @input; + +=item splice ARRAY or EXPR,OFFSET,LENGTH,LIST +X<splice> + +=item splice ARRAY or EXPR,OFFSET,LENGTH + +=item splice ARRAY or EXPR,OFFSET + +=item splice ARRAY or EXPR + +Removes the elements designated by OFFSET and LENGTH from an array, and +replaces them with the elements of LIST, if any. In list context, +returns the elements removed from the array. In scalar context, +returns the last element removed, or C<undef> if no elements are +removed. The array grows or shrinks as necessary. +If OFFSET is negative then it starts that far from the end of the array. +If LENGTH is omitted, removes everything from OFFSET onward. +If LENGTH is negative, removes the elements from OFFSET onward +except for -LENGTH elements at the end of the array. +If both OFFSET and LENGTH are omitted, removes everything. If OFFSET is +past the end of the array, Perl issues a warning, and splices at the +end of the array. + +The following equivalences hold (assuming C<< $#a >= $i >> ) + + push(@a,$x,$y) splice(@a,@a,0,$x,$y) + pop(@a) splice(@a,-1) + shift(@a) splice(@a,0,1) + unshift(@a,$x,$y) splice(@a,0,0,$x,$y) + $a[$i] = $y splice(@a,$i,1,$y) + +Example, assuming array lengths are passed before arrays: + + sub aeq { # compare two list values + my(@a) = splice(@_,0,shift); + my(@b) = splice(@_,0,shift); + return 0 unless @a == @b; # same len? + while (@a) { + return 0 if pop(@a) ne pop(@b); + } + return 1; + } + if (&aeq($len,@foo[1..$len],0+@bar,@bar)) { ... } + +Starting with Perl 5.14, C<splice> can take scalar EXPR, which must hold a +reference to an unblessed array. The argument will be dereferenced +automatically. This aspect of C<splice> is considered highly experimental. +The exact behaviour may change in a future version of Perl. + +=item split /PATTERN/,EXPR,LIMIT +X<split> + +=item split /PATTERN/,EXPR + +=item split /PATTERN/ + +=item split + +Splits the string EXPR into a list of strings and returns that list. By +default, empty leading fields are preserved, and empty trailing ones are +deleted. (If all fields are empty, they are considered to be trailing.) + +In scalar context, returns the number of fields found. + +If EXPR is omitted, splits the C<$_> string. If PATTERN is also omitted, +splits on whitespace (after skipping any leading whitespace). Anything +matching PATTERN is taken to be a delimiter separating the fields. (Note +that the delimiter may be longer than one character.) + +If LIMIT is specified and positive, it represents the maximum number +of fields the EXPR will be split into, though the actual number of +fields returned depends on the number of times PATTERN matches within +EXPR. If LIMIT is unspecified or zero, trailing null fields are +stripped (which potential users of C<pop> would do well to remember). +If LIMIT is negative, it is treated as if an arbitrarily large LIMIT +had been specified. Note that splitting an EXPR that evaluates to the +empty string always returns the empty list, regardless of the LIMIT +specified. + +A pattern matching the empty string (not to be confused with +an empty pattern C<//>, which is just one member of the set of patterns +matching the empty string), splits EXPR into individual +characters. For example: + + print join(':', split(/ */, 'hi there')), "\n"; + +produces the output 'h:i:t:h:e:r:e'. + +As a special case for C<split>, the empty pattern C<//> specifically +matches the empty string; this is not be confused with the normal use +of an empty pattern to mean the last successful match. So to split +a string into individual characters, the following: + + print join(':', split(//, 'hi there')), "\n"; + +produces the output 'h:i: :t:h:e:r:e'. + +Empty leading fields are produced when there are positive-width matches at +the beginning of the string; a zero-width match at the beginning of +the string does not produce an empty field. For example: + + print join(':', split(/(?=\w)/, 'hi there!')); + +produces the output 'h:i :t:h:e:r:e!'. Empty trailing fields, on the other +hand, are produced when there is a match at the end of the string (and +when LIMIT is given and is not 0), regardless of the length of the match. +For example: + + print join(':', split(//, 'hi there!', -1)), "\n"; + print join(':', split(/\W/, 'hi there!', -1)), "\n"; + +produce the output 'h:i: :t:h:e:r:e:!:' and 'hi:there:', respectively, +both with an empty trailing field. + +The LIMIT parameter can be used to split a line partially + + ($login, $passwd, $remainder) = split(/:/, $_, 3); + +When assigning to a list, if LIMIT is omitted, or zero, Perl supplies +a LIMIT one larger than the number of variables in the list, to avoid +unnecessary work. For the list above LIMIT would have been 4 by +default. In time critical applications it behooves you not to split +into more fields than you really need. + +If the PATTERN contains parentheses, additional list elements are +created from each matching substring in the delimiter. + + split(/([,-])/, "1-10,20", 3); + +produces the list value + + (1, '-', 10, ',', 20) + +If you had the entire header of a normal Unix email message in $header, +you could split it up into fields and their values this way: + + $header =~ s/\n(?=\s)//g; # fix continuation lines + %hdrs = (UNIX_FROM => split /^(\S*?):\s*/m, $header); + +The pattern C</PATTERN/> may be replaced with an expression to specify +patterns that vary at runtime. (To do runtime compilation only once, +use C</$variable/o>.) + +As a special case, specifying a PATTERN of space (S<C<' '>>) will split on +white space just as C<split> with no arguments does. Thus, S<C<split(' ')>> can +be used to emulate B<awk>'s default behavior, whereas S<C<split(/ /)>> +will give you as many initial null fields (empty string) as there are leading spaces. +A C<split> on C</\s+/> is like a S<C<split(' ')>> except that any leading +whitespace produces a null first field. A C<split> with no arguments +really does a S<C<split(' ', $_)>> internally. + +A PATTERN of C</^/> is treated as if it were C</^/m>, since it isn't +much use otherwise. + +Example: + + open(PASSWD, '/etc/passwd'); + while (<PASSWD>) { + chomp; + ($login, $passwd, $uid, $gid, + $gcos, $home, $shell) = split(/:/); + #... + } + +As with regular pattern matching, any capturing parentheses that are not +matched in a C<split()> will be set to C<undef> when returned: + + @fields = split /(A)|B/, "1A2B3"; + # @fields is (1, 'A', 2, undef, 3) + +=item sprintf FORMAT, LIST +X<sprintf> + +Returns a string formatted by the usual C<printf> conventions of the C +library function C<sprintf>. See below for more details +and see L<sprintf(3)> or L<printf(3)> on your system for an explanation of +the general principles. + +For example: + + # Format number with up to 8 leading zeroes + $result = sprintf("%08d", $number); + + # Round number to 3 digits after decimal point + $rounded = sprintf("%.3f", $number); + +Perl does its own C<sprintf> formatting: it emulates the C +function sprintf(3), but doesn't use it except for floating-point +numbers, and even then only standard modifiers are allowed. +Non-standard extensions in your local sprintf(3) are +therefore unavailable from Perl. + +Unlike C<printf>, C<sprintf> does not do what you probably mean when you +pass it an array as your first argument. The array is given scalar context, +and instead of using the 0th element of the array as the format, Perl will +use the count of elements in the array as the format, which is almost never +useful. + +Perl's C<sprintf> permits the following universally-known conversions: + + %% a percent sign + %c a character with the given number + %s a string + %d a signed integer, in decimal + %u an unsigned integer, in decimal + %o an unsigned integer, in octal + %x an unsigned integer, in hexadecimal + %e a floating-point number, in scientific notation + %f a floating-point number, in fixed decimal notation + %g a floating-point number, in %e or %f notation + +In addition, Perl permits the following widely-supported conversions: + + %X like %x, but using upper-case letters + %E like %e, but using an upper-case "E" + %G like %g, but with an upper-case "E" (if applicable) + %b an unsigned integer, in binary + %B like %b, but using an upper-case "B" with the # flag + %p a pointer (outputs the Perl value's address in hexadecimal) + %n special: *stores* the number of characters output so far + into the next variable in the parameter list + +Finally, for backward (and we do mean "backward") compatibility, Perl +permits these unnecessary but widely-supported conversions: + + %i a synonym for %d + %D a synonym for %ld + %U a synonym for %lu + %O a synonym for %lo + %F a synonym for %f + +Note that the number of exponent digits in the scientific notation produced +by C<%e>, C<%E>, C<%g> and C<%G> for numbers with the modulus of the +exponent less than 100 is system-dependent: it may be three or less +(zero-padded as necessary). In other words, 1.23 times ten to the +99th may be either "1.23e99" or "1.23e099". + +Between the C<%> and the format letter, you may specify several +additional attributes controlling the interpretation of the format. +In order, these are: + +=over 4 + +=item format parameter index + +An explicit format parameter index, such as C<2$>. By default sprintf +will format the next unused argument in the list, but this allows you +to take the arguments out of order: + + printf '%2$d %1$d', 12, 34; # prints "34 12" + printf '%3$d %d %1$d', 1, 2, 3; # prints "3 1 1" + +=item flags + +one or more of: + + space prefix non-negative number with a space + + prefix non-negative number with a plus sign + - left-justify within the field + 0 use zeros, not spaces, to right-justify + # ensure the leading "0" for any octal, + prefix non-zero hexadecimal with "0x" or "0X", + prefix non-zero binary with "0b" or "0B" + +For example: + + printf '<% d>', 12; # prints "< 12>" + printf '<%+d>', 12; # prints "<+12>" + printf '<%6s>', 12; # prints "< 12>" + printf '<%-6s>', 12; # prints "<12 >" + printf '<%06s>', 12; # prints "<000012>" + printf '<%#o>', 12; # prints "<014>" + printf '<%#x>', 12; # prints "<0xc>" + printf '<%#X>', 12; # prints "<0XC>" + printf '<%#b>', 12; # prints "<0b1100>" + printf '<%#B>', 12; # prints "<0B1100>" + +When a space and a plus sign are given as the flags at once, +a plus sign is used to prefix a positive number. + + printf '<%+ d>', 12; # prints "<+12>" + printf '<% +d>', 12; # prints "<+12>" + +When the # flag and a precision are given in the %o conversion, +the precision is incremented if it's necessary for the leading "0". + + printf '<%#.5o>', 012; # prints "<00012>" + printf '<%#.5o>', 012345; # prints "<012345>" + printf '<%#.0o>', 0; # prints "<0>" + +=item vector flag + +This flag tells Perl to interpret the supplied string as a vector of +integers, one for each character in the string. Perl applies the format to +each integer in turn, then joins the resulting strings with a separator (a +dot C<.> by default). This can be useful for displaying ordinal values of +characters in arbitrary strings: + + printf "%vd", "AB\x{100}"; # prints "65.66.256" + printf "version is v%vd\n", $^V; # Perl's version + +Put an asterisk C<*> before the C<v> to override the string to +use to separate the numbers: + + printf "address is %*vX\n", ":", $addr; # IPv6 address + printf "bits are %0*v8b\n", " ", $bits; # random bitstring + +You can also explicitly specify the argument number to use for +the join string using something like C<*2$v>; for example: + + printf '%*4$vX %*4$vX %*4$vX', @addr[1..3], ":"; # 3 IPv6 addresses + +=item (minimum) width + +Arguments are usually formatted to be only as wide as required to +display the given value. You can override the width by putting +a number here, or get the width from the next argument (with C<*>) +or from a specified argument (e.g., with C<*2$>): + + printf "<%s>", "a"; # prints "<a>" + printf "<%6s>", "a"; # prints "< a>" + printf "<%*s>", 6, "a"; # prints "< a>" + printf "<%*2$s>", "a", 6; # prints "< a>" + printf "<%2s>", "long"; # prints "<long>" (does not truncate) + +If a field width obtained through C<*> is negative, it has the same +effect as the C<-> flag: left-justification. + +=item precision, or maximum width +X<precision> + +You can specify a precision (for numeric conversions) or a maximum +width (for string conversions) by specifying a C<.> followed by a number. +For floating-point formats except C<g> and C<G>, this specifies +how many places right of the decimal point to show (the default being 6). +For example: + + # these examples are subject to system-specific variation + printf '<%f>', 1; # prints "<1.000000>" + printf '<%.1f>', 1; # prints "<1.0>" + printf '<%.0f>', 1; # prints "<1>" + printf '<%e>', 10; # prints "<1.000000e+01>" + printf '<%.1e>', 10; # prints "<1.0e+01>" + +For "g" and "G", this specifies the maximum number of digits to show, +including those prior to the decimal point and those after it; for +example: + + # These examples are subject to system-specific variation. + printf '<%g>', 1; # prints "<1>" + printf '<%.10g>', 1; # prints "<1>" + printf '<%g>', 100; # prints "<100>" + printf '<%.1g>', 100; # prints "<1e+02>" + printf '<%.2g>', 100.01; # prints "<1e+02>" + printf '<%.5g>', 100.01; # prints "<100.01>" + printf '<%.4g>', 100.01; # prints "<100>" + +For integer conversions, specifying a precision implies that the +output of the number itself should be zero-padded to this width, +where the 0 flag is ignored: + + printf '<%.6d>', 1; # prints "<000001>" + printf '<%+.6d>', 1; # prints "<+000001>" + printf '<%-10.6d>', 1; # prints "<000001 >" + printf '<%10.6d>', 1; # prints "< 000001>" + printf '<%010.6d>', 1; # prints "< 000001>" + printf '<%+10.6d>', 1; # prints "< +000001>" + + printf '<%.6x>', 1; # prints "<000001>" + printf '<%#.6x>', 1; # prints "<0x000001>" + printf '<%-10.6x>', 1; # prints "<000001 >" + printf '<%10.6x>', 1; # prints "< 000001>" + printf '<%010.6x>', 1; # prints "< 000001>" + printf '<%#10.6x>', 1; # prints "< 0x000001>" + +For string conversions, specifying a precision truncates the string +to fit the specified width: + + printf '<%.5s>', "truncated"; # prints "<trunc>" + printf '<%10.5s>', "truncated"; # prints "< trunc>" + +You can also get the precision from the next argument using C<.*>: + + printf '<%.6x>', 1; # prints "<000001>" + printf '<%.*x>', 6, 1; # prints "<000001>" + +If a precision obtained through C<*> is negative, it counts +as having no precision at all. + + printf '<%.*s>', 7, "string"; # prints "<string>" + printf '<%.*s>', 3, "string"; # prints "<str>" + printf '<%.*s>', 0, "string"; # prints "<>" + printf '<%.*s>', -1, "string"; # prints "<string>" + + printf '<%.*d>', 1, 0; # prints "<0>" + printf '<%.*d>', 0, 0; # prints "<>" + printf '<%.*d>', -1, 0; # prints "<0>" + +You cannot currently get the precision from a specified number, +but it is intended that this will be possible in the future, for +example using C<.*2$>: + + printf "<%.*2$x>", 1, 6; # INVALID, but in future will print "<000001>" + +=item size + +For numeric conversions, you can specify the size to interpret the +number as using C<l>, C<h>, C<V>, C<q>, C<L>, or C<ll>. For integer +conversions (C<d u o x X b i D U O>), numbers are usually assumed to be +whatever the default integer size is on your platform (usually 32 or 64 +bits), but you can override this to use instead one of the standard C types, +as supported by the compiler used to build Perl: + + hh interpret integer as C type "char" or "unsigned char" + on Perl 5.14 or later + h interpret integer as C type "short" or "unsigned short" + j interpret integer as C type "intmax_t" on Perl 5.14 + or later, and only with a C99 compiler (unportable) + l interpret integer as C type "long" or "unsigned long" + q, L, or ll interpret integer as C type "long long", "unsigned long long", + or "quad" (typically 64-bit integers) + t interpret integer as C type "ptrdiff_t" on Perl 5.14 or later + z interpret integer as C type "size_t" on Perl 5.14 or later + +As of 5.14, none of these raises an exception if they are not supported on +your platform. However, if warnings are enabled, a warning of the +C<printf> warning class is issued on an unsupported conversion flag. +Should you instead prefer an exception, do this: + + use warnings FATAL => "printf"; + +If you would like to know about a version dependency before you +start running the program, put something like this at its top: + + use 5.014; # for hh/j/t/z/ printf modifiers + +You can find out whether your Perl supports quads via L<Config>: + + use Config; + if ($Config{use64bitint} eq "define" || $Config{longsize} >= 8) { + print "Nice quads!\n"; + } + +For floating-point conversions (C<e f g E F G>), numbers are usually assumed +to be the default floating-point size on your platform (double or long double), +but you can force "long double" with C<q>, C<L>, or C<ll> if your +platform supports them. You can find out whether your Perl supports long +doubles via L<Config>: + + use Config; + print "long doubles\n" if $Config{d_longdbl} eq "define"; + +You can find out whether Perl considers "long double" to be the default +floating-point size to use on your platform via L<Config>: + + use Config; + if ($Config{uselongdouble} eq "define") { + print "long doubles by default\n"; + } + +It can also be that long doubles and doubles are the same thing: + + use Config; + ($Config{doublesize} == $Config{longdblsize}) && + print "doubles are long doubles\n"; + +The size specifier C<V> has no effect for Perl code, but is supported for +compatibility with XS code. It means "use the standard size for a Perl +integer or floating-point number", which is the default. + +=item order of arguments + +Normally, sprintf() takes the next unused argument as the value to +format for each format specification. If the format specification +uses C<*> to require additional arguments, these are consumed from +the argument list in the order they appear in the format +specification I<before> the value to format. Where an argument is +specified by an explicit index, this does not affect the normal +order for the arguments, even when the explicitly specified index +would have been the next argument. + +So: + + printf "<%*.*s>", $a, $b, $c; + +uses C<$a> for the width, C<$b> for the precision, and C<$c> +as the value to format; while: + + printf "<%*1$.*s>", $a, $b; + +would use C<$a> for the width and precision, and C<$b> as the +value to format. + +Here are some more examples; be aware that when using an explicit +index, the C<$> may need escaping: + + printf "%2\$d %d\n", 12, 34; # will print "34 12\n" + printf "%2\$d %d %d\n", 12, 34; # will print "34 12 34\n" + printf "%3\$d %d %d\n", 12, 34, 56; # will print "56 12 34\n" + printf "%2\$*3\$d %d\n", 12, 34, 3; # will print " 34 12\n" + +=back + +If C<use locale> is in effect and POSIX::setlocale() has been called, +the character used for the decimal separator in formatted floating-point +numbers is affected by the LC_NUMERIC locale. See L<perllocale> +and L<POSIX>. + +=item sqrt EXPR +X<sqrt> X<root> X<square root> + +=item sqrt + +Return the positive square root of EXPR. If EXPR is omitted, uses +C<$_>. Works only for non-negative operands unless you've +loaded the C<Math::Complex> module. + + use Math::Complex; + print sqrt(-4); # prints 2i + +=item srand EXPR +X<srand> X<seed> X<randseed> + +=item srand + +Sets and returns the random number seed for the C<rand> operator. + +The point of the function is to "seed" the C<rand> function so that +C<rand> can produce a different sequence each time you run your +program. When called with a parameter, C<srand> uses that for the seed; +otherwise it (semi-)randomly chooses a seed. In either case, starting with +Perl 5.14, it returns the seed. + +If C<srand()> is not called explicitly, it is called implicitly without a +parameter at the first use of the C<rand> operator. However, this was not true +of versions of Perl before 5.004, so if your script will run under older +Perl versions, it should call C<srand>; otherwise most programs won't call +C<srand()> at all. + +But there are a few situations in recent Perls where programs are likely to +want to call C<srand>. One is for generating predictable results generally for +testing or debugging. There, you use C<srand($seed)>, with the same C<$seed> +each time. Another case is that you may want to call C<srand()> +after a C<fork()> to avoid child processes sharing the same seed value as the +parent (and consequently each other). + +Do B<not> call C<srand()> (i.e., without an argument) more than once per +process. The internal state of the random number generator should +contain more entropy than can be provided by any seed, so calling +C<srand()> again actually I<loses> randomness. + +Most implementations of C<srand> take an integer and will silently +truncate decimal numbers. This means C<srand(42)> will usually +produce the same results as C<srand(42.1)>. To be safe, always pass +C<srand> an integer. + +In versions of Perl prior to 5.004 the default seed was just the +current C<time>. This isn't a particularly good seed, so many old +programs supply their own seed value (often C<time ^ $$> or C<time ^ +($$ + ($$ << 15))>), but that isn't necessary any more. + +Frequently called programs (like CGI scripts) that simply use + + time ^ $$ + +for a seed can fall prey to the mathematical property that + + a^b == (a+1)^(b+1) + +one-third of the time. So don't do that. + +A typical use of the returned seed is for a test program which has too many +combinations to test comprehensively in the time available to it each run. It +can test a random subset each time, and should there be a failure, log the seed +used for that run so that it can later be used to reproduce the same results. + +B<C<rand()> is not cryptographically secure. You should not rely +on it in security-sensitive situations.> As of this writing, a +number of third-party CPAN modules offer random number generators +intended by their authors to be cryptographically secure, +including: L<Data::Entropy>, L<Crypt::Random>, L<Math::Random::Secure>, +and L<Math::TrulyRandom>. + +=item stat FILEHANDLE +X<stat> X<file, status> X<ctime> + +=item stat EXPR + +=item stat DIRHANDLE + +=item stat + +Returns a 13-element list giving the status info for a file, either +the file opened via FILEHANDLE or DIRHANDLE, or named by EXPR. If EXPR is +omitted, it stats C<$_> (not C<_>!). Returns the empty list if C<stat> fails. Typically +used as follows: + + ($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size, + $atime,$mtime,$ctime,$blksize,$blocks) + = stat($filename); + +Not all fields are supported on all filesystem types. Here are the +meanings of the fields: + + 0 dev device number of filesystem + 1 ino inode number + 2 mode file mode (type and permissions) + 3 nlink number of (hard) links to the file + 4 uid numeric user ID of file's owner + 5 gid numeric group ID of file's owner + 6 rdev the device identifier (special files only) + 7 size total size of file, in bytes + 8 atime last access time in seconds since the epoch + 9 mtime last modify time in seconds since the epoch + 10 ctime inode change time in seconds since the epoch (*) + 11 blksize preferred block size for file system I/O + 12 blocks actual number of blocks allocated + +(The epoch was at 00:00 January 1, 1970 GMT.) + +(*) Not all fields are supported on all filesystem types. Notably, the +ctime field is non-portable. In particular, you cannot expect it to be a +"creation time"; see L<perlport/"Files and Filesystems"> for details. + +If C<stat> is passed the special filehandle consisting of an underline, no +stat is done, but the current contents of the stat structure from the +last C<stat>, C<lstat>, or filetest are returned. Example: + + if (-x $file && (($d) = stat(_)) && $d < 0) { + print "$file is executable NFS file\n"; + } + +(This works on machines only for which the device number is negative +under NFS.) + +Because the mode contains both the file type and its permissions, you +should mask off the file type portion and (s)printf using a C<"%o"> +if you want to see the real permissions. + + $mode = (stat($filename))[2]; + printf "Permissions are %04o\n", $mode & 07777; + +In scalar context, C<stat> returns a boolean value indicating success +or failure, and, if successful, sets the information associated with +the special filehandle C<_>. + +The L<File::stat> module provides a convenient, by-name access mechanism: + + use File::stat; + $sb = stat($filename); + printf "File is %s, size is %s, perm %04o, mtime %s\n", + $filename, $sb->size, $sb->mode & 07777, + scalar localtime $sb->mtime; + +You can import symbolic mode constants (C<S_IF*>) and functions +(C<S_IS*>) from the Fcntl module: + + use Fcntl ':mode'; + + $mode = (stat($filename))[2]; + + $user_rwx = ($mode & S_IRWXU) >> 6; + $group_read = ($mode & S_IRGRP) >> 3; + $other_execute = $mode & S_IXOTH; + + printf "Permissions are %04o\n", S_IMODE($mode), "\n"; + + $is_setuid = $mode & S_ISUID; + $is_directory = S_ISDIR($mode); + +You could write the last two using the C<-u> and C<-d> operators. +Commonly available C<S_IF*> constants are: + + # Permissions: read, write, execute, for user, group, others. + + S_IRWXU S_IRUSR S_IWUSR S_IXUSR + S_IRWXG S_IRGRP S_IWGRP S_IXGRP + S_IRWXO S_IROTH S_IWOTH S_IXOTH + + # Setuid/Setgid/Stickiness/SaveText. + # Note that the exact meaning of these is system-dependent. + + S_ISUID S_ISGID S_ISVTX S_ISTXT + + # File types. Not all are necessarily available on + # your system. + + S_IFREG S_IFDIR S_IFLNK S_IFBLK S_IFCHR + S_IFIFO S_IFSOCK S_IFWHT S_ENFMT + + # The following are compatibility aliases for S_IRUSR, + # S_IWUSR, and S_IXUSR. + + S_IREAD S_IWRITE S_IEXEC + +and the C<S_IF*> functions are + + S_IMODE($mode) the part of $mode containing the permission + bits and the setuid/setgid/sticky bits + + S_IFMT($mode) the part of $mode containing the file type + which can be bit-anded with (for example) + S_IFREG or with the following functions + + # The operators -f, -d, -l, -b, -c, -p, and -S. + + S_ISREG($mode) S_ISDIR($mode) S_ISLNK($mode) + S_ISBLK($mode) S_ISCHR($mode) S_ISFIFO($mode) S_ISSOCK($mode) + + # No direct -X operator counterpart, but for the first one + # the -g operator is often equivalent. The ENFMT stands for + # record flocking enforcement, a platform-dependent feature. + + S_ISENFMT($mode) S_ISWHT($mode) + +See your native chmod(2) and stat(2) documentation for more details +about the C<S_*> constants. To get status info for a symbolic link +instead of the target file behind the link, use the C<lstat> function. + +Portability issues: L<perlport/stat>. + +=item state EXPR +X<state> + +=item state TYPE EXPR + +=item state EXPR : ATTRS + +=item state TYPE EXPR : ATTRS + +C<state> declares a lexically scoped variable, just like C<my>. +However, those variables will never be reinitialized, contrary to +lexical variables that are reinitialized each time their enclosing block +is entered. +See L<perlsub/"Persistent Private Variables"> for details. + +C<state> variables are enabled only when the C<use feature "state"> pragma +is in effect, unless the keyword is written as C<CORE::state>. +See also L<feature>. + +=item study SCALAR +X<study> + +=item study + +Takes extra time to study SCALAR (C<$_> if unspecified) in anticipation of +doing many pattern matches on the string before it is next modified. +This may or may not save time, depending on the nature and number of +patterns you are searching and the distribution of character +frequencies in the string to be searched; you probably want to compare +run times with and without it to see which is faster. Those loops +that scan for many short constant strings (including the constant +parts of more complex patterns) will benefit most. +(The way C<study> works is this: a linked list of every +character in the string to be searched is made, so we know, for +example, where all the C<'k'> characters are. From each search string, +the rarest character is selected, based on some static frequency tables +constructed from some C programs and English text. Only those places +that contain this "rarest" character are examined.) + +For example, here is a loop that inserts index producing entries +before any line containing a certain pattern: + + while (<>) { + study; + print ".IX foo\n" if /\bfoo\b/; + print ".IX bar\n" if /\bbar\b/; + print ".IX blurfl\n" if /\bblurfl\b/; + # ... + print; + } + +In searching for C</\bfoo\b/>, only locations in C<$_> that contain C<f> +will be looked at, because C<f> is rarer than C<o>. In general, this is +a big win except in pathological cases. The only question is whether +it saves you more time than it took to build the linked list in the +first place. + +Note that if you have to look for strings that you don't know till +runtime, you can build an entire loop as a string and C<eval> that to +avoid recompiling all your patterns all the time. Together with +undefining C<$/> to input entire files as one record, this can be quite +fast, often faster than specialized programs like fgrep(1). The following +scans a list of files (C<@files>) for a list of words (C<@words>), and prints +out the names of those files that contain a match: + + $search = 'while (<>) { study;'; + foreach $word (@words) { + $search .= "++\$seen{\$ARGV} if /\\b$word\\b/;\n"; + } + $search .= "}"; + @ARGV = @files; + undef $/; + eval $search; # this screams + $/ = "\n"; # put back to normal input delimiter + foreach $file (sort keys(%seen)) { + print $file, "\n"; + } + +=item sub NAME BLOCK +X<sub> + +=item sub NAME (PROTO) BLOCK + +=item sub NAME : ATTRS BLOCK + +=item sub NAME (PROTO) : ATTRS BLOCK + +This is subroutine definition, not a real function I<per se>. Without a +BLOCK it's just a forward declaration. Without a NAME, it's an anonymous +function declaration, so does return a value: the CODE ref of the closure +just created. + +See L<perlsub> and L<perlref> for details about subroutines and +references; see L<attributes> and L<Attribute::Handlers> for more +information about attributes. + +=item __SUB__ +X<__SUB__> + +A special token that returns the a reference to the current subroutine, or +C<undef> outside of a subroutine. + +This token is only available under C<use v5.16> or the "current_sub" +feature. See L<feature>. + +=item substr EXPR,OFFSET,LENGTH,REPLACEMENT +X<substr> X<substring> X<mid> X<left> X<right> + +=item substr EXPR,OFFSET,LENGTH + +=item substr EXPR,OFFSET + +Extracts a substring out of EXPR and returns it. First character is at +offset zero. If OFFSET is negative, starts +that far back from the end of the string. If LENGTH is omitted, returns +everything through the end of the string. If LENGTH is negative, leaves that +many characters off the end of the string. + + my $s = "The black cat climbed the green tree"; + my $color = substr $s, 4, 5; # black + my $middle = substr $s, 4, -11; # black cat climbed the + my $end = substr $s, 14; # climbed the green tree + my $tail = substr $s, -4; # tree + my $z = substr $s, -4, 2; # tr + +You can use the substr() function as an lvalue, in which case EXPR +must itself be an lvalue. If you assign something shorter than LENGTH, +the string will shrink, and if you assign something longer than LENGTH, +the string will grow to accommodate it. To keep the string the same +length, you may need to pad or chop your value using C<sprintf>. + +If OFFSET and LENGTH specify a substring that is partly outside the +string, only the part within the string is returned. If the substring +is beyond either end of the string, substr() returns the undefined +value and produces a warning. When used as an lvalue, specifying a +substring that is entirely outside the string raises an exception. +Here's an example showing the behavior for boundary cases: + + my $name = 'fred'; + substr($name, 4) = 'dy'; # $name is now 'freddy' + my $null = substr $name, 6, 2; # returns "" (no warning) + my $oops = substr $name, 7; # returns undef, with warning + substr($name, 7) = 'gap'; # raises an exception + +An alternative to using substr() as an lvalue is to specify the +replacement string as the 4th argument. This allows you to replace +parts of the EXPR and return what was there before in one operation, +just as you can with splice(). + + my $s = "The black cat climbed the green tree"; + my $z = substr $s, 14, 7, "jumped from"; # climbed + # $s is now "The black cat jumped from the green tree" + +Note that the lvalue returned by the three-argument version of substr() acts as +a 'magic bullet'; each time it is assigned to, it remembers which part +of the original string is being modified; for example: + + $x = '1234'; + for (substr($x,1,2)) { + $_ = 'a'; print $x,"\n"; # prints 1a4 + $_ = 'xyz'; print $x,"\n"; # prints 1xyz4 + $x = '56789'; + $_ = 'pq'; print $x,"\n"; # prints 5pq9 + } + +Prior to Perl version 5.9.1, the result of using an lvalue multiple times was +unspecified. + +=item symlink OLDFILE,NEWFILE +X<symlink> X<link> X<symbolic link> X<link, symbolic> + +Creates a new filename symbolically linked to the old filename. +Returns C<1> for success, C<0> otherwise. On systems that don't support +symbolic links, raises an exception. To check for that, +use eval: + + $symlink_exists = eval { symlink("",""); 1 }; + +Portability issues: L<perlport/symlink>. + +=item syscall NUMBER, LIST +X<syscall> X<system call> + +Calls the system call specified as the first element of the list, +passing the remaining elements as arguments to the system call. If +unimplemented, raises an exception. The arguments are interpreted +as follows: if a given argument is numeric, the argument is passed as +an int. If not, the pointer to the string value is passed. You are +responsible to make sure a string is pre-extended long enough to +receive any result that might be written into a string. You can't use a +string literal (or other read-only string) as an argument to C<syscall> +because Perl has to assume that any string pointer might be written +through. If your +integer arguments are not literals and have never been interpreted in a +numeric context, you may need to add C<0> to them to force them to look +like numbers. This emulates the C<syswrite> function (or vice versa): + + require 'syscall.ph'; # may need to run h2ph + $s = "hi there\n"; + syscall(&SYS_write, fileno(STDOUT), $s, length $s); + +Note that Perl supports passing of up to only 14 arguments to your syscall, +which in practice should (usually) suffice. + +Syscall returns whatever value returned by the system call it calls. +If the system call fails, C<syscall> returns C<-1> and sets C<$!> (errno). +Note that some system calls I<can> legitimately return C<-1>. The proper +way to handle such calls is to assign C<$!=0> before the call, then +check the value of C<$!> if C<syscall> returns C<-1>. + +There's a problem with C<syscall(&SYS_pipe)>: it returns the file +number of the read end of the pipe it creates, but there is no way +to retrieve the file number of the other end. You can avoid this +problem by using C<pipe> instead. + +Portability issues: L<perlport/syscall>. + +=item sysopen FILEHANDLE,FILENAME,MODE +X<sysopen> + +=item sysopen FILEHANDLE,FILENAME,MODE,PERMS + +Opens the file whose filename is given by FILENAME, and associates it with +FILEHANDLE. If FILEHANDLE is an expression, its value is used as the real +filehandle wanted; an undefined scalar will be suitably autovivified. This +function calls the underlying operating system's I<open>(2) function with the +parameters FILENAME, MODE, and PERMS. + +The possible values and flag bits of the MODE parameter are +system-dependent; they are available via the standard module C<Fcntl>. See +the documentation of your operating system's I<open>(2) syscall to see +which values and flag bits are available. You may combine several flags +using the C<|>-operator. + +Some of the most common values are C<O_RDONLY> for opening the file in +read-only mode, C<O_WRONLY> for opening the file in write-only mode, +and C<O_RDWR> for opening the file in read-write mode. +X<O_RDONLY> X<O_RDWR> X<O_WRONLY> + +For historical reasons, some values work on almost every system +supported by Perl: 0 means read-only, 1 means write-only, and 2 +means read/write. We know that these values do I<not> work under +OS/390 & VM/ESA Unix and on the Macintosh; you probably don't want to +use them in new code. + +If the file named by FILENAME does not exist and the C<open> call creates +it (typically because MODE includes the C<O_CREAT> flag), then the value of +PERMS specifies the permissions of the newly created file. If you omit +the PERMS argument to C<sysopen>, Perl uses the octal value C<0666>. +These permission values need to be in octal, and are modified by your +process's current C<umask>. +X<O_CREAT> + +In many systems the C<O_EXCL> flag is available for opening files in +exclusive mode. This is B<not> locking: exclusiveness means here that +if the file already exists, sysopen() fails. C<O_EXCL> may not work +on network filesystems, and has no effect unless the C<O_CREAT> flag +is set as well. Setting C<O_CREAT|O_EXCL> prevents the file from +being opened if it is a symbolic link. It does not protect against +symbolic links in the file's path. +X<O_EXCL> + +Sometimes you may want to truncate an already-existing file. This +can be done using the C<O_TRUNC> flag. The behavior of +C<O_TRUNC> with C<O_RDONLY> is undefined. +X<O_TRUNC> + +You should seldom if ever use C<0644> as argument to C<sysopen>, because +that takes away the user's option to have a more permissive umask. +Better to omit it. See the perlfunc(1) entry on C<umask> for more +on this. + +Note that C<sysopen> depends on the fdopen() C library function. +On many Unix systems, fdopen() is known to fail when file descriptors +exceed a certain value, typically 255. If you need more file +descriptors than that, consider rebuilding Perl to use the C<sfio> +library, or perhaps using the POSIX::open() function. + +See L<perlopentut> for a kinder, gentler explanation of opening files. + +Portability issues: L<perlport/sysopen>. + +=item sysread FILEHANDLE,SCALAR,LENGTH,OFFSET +X<sysread> + +=item sysread FILEHANDLE,SCALAR,LENGTH + +Attempts to read LENGTH bytes of data into variable SCALAR from the +specified FILEHANDLE, using the read(2). It bypasses +buffered IO, so mixing this with other kinds of reads, C<print>, +C<write>, C<seek>, C<tell>, or C<eof> can cause confusion because the +perlio or stdio layers usually buffers data. Returns the number of +bytes actually read, C<0> at end of file, or undef if there was an +error (in the latter case C<$!> is also set). SCALAR will be grown or +shrunk so that the last byte actually read is the last byte of the +scalar after the read. + +An OFFSET may be specified to place the read data at some place in the +string other than the beginning. A negative OFFSET specifies +placement at that many characters counting backwards from the end of +the string. A positive OFFSET greater than the length of SCALAR +results in the string being padded to the required size with C<"\0"> +bytes before the result of the read is appended. + +There is no syseof() function, which is ok, since eof() doesn't work +well on device files (like ttys) anyway. Use sysread() and check +for a return value for 0 to decide whether you're done. + +Note that if the filehandle has been marked as C<:utf8> Unicode +characters are read instead of bytes (the LENGTH, OFFSET, and the +return value of sysread() are in Unicode characters). +The C<:encoding(...)> layer implicitly introduces the C<:utf8> layer. +See L</binmode>, L</open>, and the C<open> pragma, L<open>. + +=item sysseek FILEHANDLE,POSITION,WHENCE +X<sysseek> X<lseek> + +Sets FILEHANDLE's system position in bytes using lseek(2). FILEHANDLE may +be an expression whose value gives the name of the filehandle. The values +for WHENCE are C<0> to set the new position to POSITION; C<1> to set the it +to the current position plus POSITION; and C<2> to set it to EOF plus +POSITION, typically negative. + +Note the I<in bytes>: even if the filehandle has been set to operate +on characters (for example by using the C<:encoding(utf8)> I/O layer), +tell() will return byte offsets, not character offsets (because +implementing that would render sysseek() unacceptably slow). + +sysseek() bypasses normal buffered IO, so mixing it with reads other +than C<sysread> (for example C<< <> >> or read()) C<print>, C<write>, +C<seek>, C<tell>, or C<eof> may cause confusion. + +For WHENCE, you may also use the constants C<SEEK_SET>, C<SEEK_CUR>, +and C<SEEK_END> (start of the file, current position, end of the file) +from the Fcntl module. Use of the constants is also more portable +than relying on 0, 1, and 2. For example to define a "systell" function: + + use Fcntl 'SEEK_CUR'; + sub systell { sysseek($_[0], 0, SEEK_CUR) } + +Returns the new position, or the undefined value on failure. A position +of zero is returned as the string C<"0 but true">; thus C<sysseek> returns +true on success and false on failure, yet you can still easily determine +the new position. + +=item system LIST +X<system> X<shell> + +=item system PROGRAM LIST + +Does exactly the same thing as C<exec LIST>, except that a fork is +done first and the parent process waits for the child process to +exit. Note that argument processing varies depending on the +number of arguments. If there is more than one argument in LIST, +or if LIST is an array with more than one value, starts the program +given by the first element of the list with arguments given by the +rest of the list. If there is only one scalar argument, the argument +is checked for shell metacharacters, and if there are any, the +entire argument is passed to the system's command shell for parsing +(this is C</bin/sh -c> on Unix platforms, but varies on other +platforms). If there are no shell metacharacters in the argument, +it is split into words and passed directly to C<execvp>, which is +more efficient. + +Beginning with v5.6.0, Perl will attempt to flush all files opened for +output before any operation that may do a fork, but this may not be +supported on some platforms (see L<perlport>). To be safe, you may need +to set C<$|> ($AUTOFLUSH in English) or call the C<autoflush()> method +of C<IO::Handle> on any open handles. + +The return value is the exit status of the program as returned by the +C<wait> call. To get the actual exit value, shift right by eight (see +below). See also L</exec>. This is I<not> what you want to use to capture +the output from a command; for that you should use merely backticks or +C<qx//>, as described in L<perlop/"`STRING`">. Return value of -1 +indicates a failure to start the program or an error of the wait(2) system +call (inspect $! for the reason). + +If you'd like to make C<system> (and many other bits of Perl) die on error, +have a look at the L<autodie> pragma. + +Like C<exec>, C<system> allows you to lie to a program about its name if +you use the C<system PROGRAM LIST> syntax. Again, see L</exec>. + +Since C<SIGINT> and C<SIGQUIT> are ignored during the execution of +C<system>, if you expect your program to terminate on receipt of these +signals you will need to arrange to do so yourself based on the return +value. + + @args = ("command", "arg1", "arg2"); + system(@args) == 0 + or die "system @args failed: $?" + +If you'd like to manually inspect C<system>'s failure, you can check all +possible failure modes by inspecting C<$?> like this: + + if ($? == -1) { + print "failed to execute: $!\n"; + } + elsif ($? & 127) { + printf "child died with signal %d, %s coredump\n", + ($? & 127), ($? & 128) ? 'with' : 'without'; + } + else { + printf "child exited with value %d\n", $? >> 8; + } + +Alternatively, you may inspect the value of C<${^CHILD_ERROR_NATIVE}> +with the C<W*()> calls from the POSIX module. + +When C<system>'s arguments are executed indirectly by the shell, +results and return codes are subject to its quirks. +See L<perlop/"`STRING`"> and L</exec> for details. + +Since C<system> does a C<fork> and C<wait> it may affect a C<SIGCHLD> +handler. See L<perlipc> for details. + +Portability issues: L<perlport/system>. + +=item syswrite FILEHANDLE,SCALAR,LENGTH,OFFSET +X<syswrite> + +=item syswrite FILEHANDLE,SCALAR,LENGTH + +=item syswrite FILEHANDLE,SCALAR + +Attempts to write LENGTH bytes of data from variable SCALAR to the +specified FILEHANDLE, using write(2). If LENGTH is +not specified, writes whole SCALAR. It bypasses buffered IO, so +mixing this with reads (other than C<sysread())>, C<print>, C<write>, +C<seek>, C<tell>, or C<eof> may cause confusion because the perlio and +stdio layers usually buffer data. Returns the number of bytes +actually written, or C<undef> if there was an error (in this case the +errno variable C<$!> is also set). If the LENGTH is greater than the +data available in the SCALAR after the OFFSET, only as much data as is +available will be written. + +An OFFSET may be specified to write the data from some part of the +string other than the beginning. A negative OFFSET specifies writing +that many characters counting backwards from the end of the string. +If SCALAR is of length zero, you can only use an OFFSET of 0. + +B<WARNING>: If the filehandle is marked C<:utf8>, Unicode characters +encoded in UTF-8 are written instead of bytes, and the LENGTH, OFFSET, and +return value of syswrite() are in (UTF8-encoded Unicode) characters. +The C<:encoding(...)> layer implicitly introduces the C<:utf8> layer. +Alternately, if the handle is not marked with an encoding but you +attempt to write characters with code points over 255, raises an exception. +See L</binmode>, L</open>, and the C<open> pragma, L<open>. + +=item tell FILEHANDLE +X<tell> + +=item tell + +Returns the current position I<in bytes> for FILEHANDLE, or -1 on +error. FILEHANDLE may be an expression whose value gives the name of +the actual filehandle. If FILEHANDLE is omitted, assumes the file +last read. + +Note the I<in bytes>: even if the filehandle has been set to +operate on characters (for example by using the C<:encoding(utf8)> open +layer), tell() will return byte offsets, not character offsets (because +that would render seek() and tell() rather slow). + +The return value of tell() for the standard streams like the STDIN +depends on the operating system: it may return -1 or something else. +tell() on pipes, fifos, and sockets usually returns -1. + +There is no C<systell> function. Use C<sysseek(FH, 0, 1)> for that. + +Do not use tell() (or other buffered I/O operations) on a filehandle +that has been manipulated by sysread(), syswrite(), or sysseek(). +Those functions ignore the buffering, while tell() does not. + +=item telldir DIRHANDLE +X<telldir> + +Returns the current position of the C<readdir> routines on DIRHANDLE. +Value may be given to C<seekdir> to access a particular location in a +directory. C<telldir> has the same caveats about possible directory +compaction as the corresponding system library routine. + +=item tie VARIABLE,CLASSNAME,LIST +X<tie> + +This function binds a variable to a package class that will provide the +implementation for the variable. VARIABLE is the name of the variable +to be enchanted. CLASSNAME is the name of a class implementing objects +of correct type. Any additional arguments are passed to the C<new> +method of the class (meaning C<TIESCALAR>, C<TIEHANDLE>, C<TIEARRAY>, +or C<TIEHASH>). Typically these are arguments such as might be passed +to the C<dbm_open()> function of C. The object returned by the C<new> +method is also returned by the C<tie> function, which would be useful +if you want to access other methods in CLASSNAME. + +Note that functions such as C<keys> and C<values> may return huge lists +when used on large objects, like DBM files. You may prefer to use the +C<each> function to iterate over such. Example: + + # print out history file offsets + use NDBM_File; + tie(%HIST, 'NDBM_File', '/usr/lib/news/history', 1, 0); + while (($key,$val) = each %HIST) { + print $key, ' = ', unpack('L',$val), "\n"; + } + untie(%HIST); + +A class implementing a hash should have the following methods: + + TIEHASH classname, LIST + FETCH this, key + STORE this, key, value + DELETE this, key + CLEAR this + EXISTS this, key + FIRSTKEY this + NEXTKEY this, lastkey + SCALAR this + DESTROY this + UNTIE this + +A class implementing an ordinary array should have the following methods: + + TIEARRAY classname, LIST + FETCH this, key + STORE this, key, value + FETCHSIZE this + STORESIZE this, count + CLEAR this + PUSH this, LIST + POP this + SHIFT this + UNSHIFT this, LIST + SPLICE this, offset, length, LIST + EXTEND this, count + DESTROY this + UNTIE this + +A class implementing a filehandle should have the following methods: + + TIEHANDLE classname, LIST + READ this, scalar, length, offset + READLINE this + GETC this + WRITE this, scalar, length, offset + PRINT this, LIST + PRINTF this, format, LIST + BINMODE this + EOF this + FILENO this + SEEK this, position, whence + TELL this + OPEN this, mode, LIST + CLOSE this + DESTROY this + UNTIE this + +A class implementing a scalar should have the following methods: + + TIESCALAR classname, LIST + FETCH this, + STORE this, value + DESTROY this + UNTIE this + +Not all methods indicated above need be implemented. See L<perltie>, +L<Tie::Hash>, L<Tie::Array>, L<Tie::Scalar>, and L<Tie::Handle>. + +Unlike C<dbmopen>, the C<tie> function will not C<use> or C<require> a module +for you; you need to do that explicitly yourself. See L<DB_File> +or the F<Config> module for interesting C<tie> implementations. + +For further details see L<perltie>, L<"tied VARIABLE">. + +=item tied VARIABLE +X<tied> + +Returns a reference to the object underlying VARIABLE (the same value +that was originally returned by the C<tie> call that bound the variable +to a package.) Returns the undefined value if VARIABLE isn't tied to a +package. + +=item time +X<time> X<epoch> + +Returns the number of non-leap seconds since whatever time the system +considers to be the epoch, suitable for feeding to C<gmtime> and +C<localtime>. On most systems the epoch is 00:00:00 UTC, January 1, 1970; +a prominent exception being Mac OS Classic which uses 00:00:00, January 1, +1904 in the current local time zone for its epoch. + +For measuring time in better granularity than one second, use the +L<Time::HiRes> module from Perl 5.8 onwards (or from CPAN before then), or, +if you have gettimeofday(2), you may be able to use the C<syscall> +interface of Perl. See L<perlfaq8> for details. + +For date and time processing look at the many related modules on CPAN. +For a comprehensive date and time representation look at the +L<DateTime> module. + +=item times +X<times> + +Returns a four-element list giving the user and system times in +seconds for this process and any exited children of this process. + + ($user,$system,$cuser,$csystem) = times; + +In scalar context, C<times> returns C<$user>. + +Children's times are only included for terminated children. + +Portability issues: L<perlport/times>. + +=item tr/// + +The transliteration operator. Same as C<y///>. See +L<perlop/"Quote and Quote-like Operators">. + +=item truncate FILEHANDLE,LENGTH +X<truncate> + +=item truncate EXPR,LENGTH + +Truncates the file opened on FILEHANDLE, or named by EXPR, to the +specified length. Raises an exception if truncate isn't implemented +on your system. Returns true if successful, C<undef> on error. + +The behavior is undefined if LENGTH is greater than the length of the +file. + +The position in the file of FILEHANDLE is left unchanged. You may want to +call L<seek|/"seek FILEHANDLE,POSITION,WHENCE"> before writing to the file. + +Portability issues: L<perlport/truncate>. + +=item uc EXPR +X<uc> X<uppercase> X<toupper> + +=item uc + +Returns an uppercased version of EXPR. This is the internal function +implementing the C<\U> escape in double-quoted strings. +It does not attempt to do titlecase mapping on initial letters. See +L</ucfirst> for that. + +If EXPR is omitted, uses C<$_>. + +This function behaves the same way under various pragma, such as in a locale, +as L</lc> does. + +=item ucfirst EXPR +X<ucfirst> X<uppercase> + +=item ucfirst + +Returns the value of EXPR with the first character in uppercase +(titlecase in Unicode). This is the internal function implementing +the C<\u> escape in double-quoted strings. + +If EXPR is omitted, uses C<$_>. + +This function behaves the same way under various pragma, such as in a locale, +as L</lc> does. + +=item umask EXPR +X<umask> + +=item umask + +Sets the umask for the process to EXPR and returns the previous value. +If EXPR is omitted, merely returns the current umask. + +The Unix permission C<rwxr-x---> is represented as three sets of three +bits, or three octal digits: C<0750> (the leading 0 indicates octal +and isn't one of the digits). The C<umask> value is such a number +representing disabled permissions bits. The permission (or "mode") +values you pass C<mkdir> or C<sysopen> are modified by your umask, so +even if you tell C<sysopen> to create a file with permissions C<0777>, +if your umask is C<0022>, then the file will actually be created with +permissions C<0755>. If your C<umask> were C<0027> (group can't +write; others can't read, write, or execute), then passing +C<sysopen> C<0666> would create a file with mode C<0640> (because +C<0666 &~ 027> is C<0640>). + +Here's some advice: supply a creation mode of C<0666> for regular +files (in C<sysopen>) and one of C<0777> for directories (in +C<mkdir>) and executable files. This gives users the freedom of +choice: if they want protected files, they might choose process umasks +of C<022>, C<027>, or even the particularly antisocial mask of C<077>. +Programs should rarely if ever make policy decisions better left to +the user. The exception to this is when writing files that should be +kept private: mail files, web browser cookies, I<.rhosts> files, and +so on. + +If umask(2) is not implemented on your system and you are trying to +restrict access for I<yourself> (i.e., C<< (EXPR & 0700) > 0 >>), +raises an exception. If umask(2) is not implemented and you are +not trying to restrict access for yourself, returns C<undef>. + +Remember that a umask is a number, usually given in octal; it is I<not> a +string of octal digits. See also L</oct>, if all you have is a string. + +Portability issues: L<perlport/umask>. + +=item undef EXPR +X<undef> X<undefine> + +=item undef + +Undefines the value of EXPR, which must be an lvalue. Use only on a +scalar value, an array (using C<@>), a hash (using C<%>), a subroutine +(using C<&>), or a typeglob (using C<*>). Saying C<undef $hash{$key}> +will probably not do what you expect on most predefined variables or +DBM list values, so don't do that; see L</delete>. Always returns the +undefined value. You can omit the EXPR, in which case nothing is +undefined, but you still get an undefined value that you could, for +instance, return from a subroutine, assign to a variable, or pass as a +parameter. Examples: + + undef $foo; + undef $bar{'blurfl'}; # Compare to: delete $bar{'blurfl'}; + undef @ary; + undef %hash; + undef &mysub; + undef *xyz; # destroys $xyz, @xyz, %xyz, &xyz, etc. + return (wantarray ? (undef, $errmsg) : undef) if $they_blew_it; + select undef, undef, undef, 0.25; + ($a, $b, undef, $c) = &foo; # Ignore third value returned + +Note that this is a unary operator, not a list operator. + +=item unlink LIST +X<unlink> X<delete> X<remove> X<rm> X<del> + +=item unlink + +Deletes a list of files. On success, it returns the number of files +it successfully deleted. On failure, it returns false and sets C<$!> +(errno): + + my $unlinked = unlink 'a', 'b', 'c'; + unlink @goners; + unlink glob "*.bak"; + +On error, C<unlink> will not tell you which files it could not remove. +If you want to know which files you could not remove, try them one +at a time: + + foreach my $file ( @goners ) { + unlink $file or warn "Could not unlink $file: $!"; + } + +Note: C<unlink> will not attempt to delete directories unless you are +superuser and the B<-U> flag is supplied to Perl. Even if these +conditions are met, be warned that unlinking a directory can inflict +damage on your filesystem. Finally, using C<unlink> on directories is +not supported on many operating systems. Use C<rmdir> instead. + +If LIST is omitted, C<unlink> uses C<$_>. + +=item unpack TEMPLATE,EXPR +X<unpack> + +=item unpack TEMPLATE + +C<unpack> does the reverse of C<pack>: it takes a string +and expands it out into a list of values. +(In scalar context, it returns merely the first value produced.) + +If EXPR is omitted, unpacks the C<$_> string. +See L<perlpacktut> for an introduction to this function. + +The string is broken into chunks described by the TEMPLATE. Each chunk +is converted separately to a value. Typically, either the string is a result +of C<pack>, or the characters of the string represent a C structure of some +kind. + +The TEMPLATE has the same format as in the C<pack> function. +Here's a subroutine that does substring: + + sub substr { + my($what,$where,$howmuch) = @_; + unpack("x$where a$howmuch", $what); + } + +and then there's + + sub ordinal { unpack("W",$_[0]); } # same as ord() + +In addition to fields allowed in pack(), you may prefix a field with +a %<number> to indicate that +you want a <number>-bit checksum of the items instead of the items +themselves. Default is a 16-bit checksum. Checksum is calculated by +summing numeric values of expanded values (for string fields the sum of +C<ord($char)> is taken; for bit fields the sum of zeroes and ones). + +For example, the following +computes the same number as the System V sum program: + + $checksum = do { + local $/; # slurp! + unpack("%32W*",<>) % 65535; + }; + +The following efficiently counts the number of set bits in a bit vector: + + $setbits = unpack("%32b*", $selectmask); + +The C<p> and C<P> formats should be used with care. Since Perl +has no way of checking whether the value passed to C<unpack()> +corresponds to a valid memory location, passing a pointer value that's +not known to be valid is likely to have disastrous consequences. + +If there are more pack codes or if the repeat count of a field or a group +is larger than what the remainder of the input string allows, the result +is not well defined: the repeat count may be decreased, or +C<unpack()> may produce empty strings or zeros, or it may raise an exception. +If the input string is longer than one described by the TEMPLATE, +the remainder of that input string is ignored. + +See L</pack> for more examples and notes. + +=item untie VARIABLE +X<untie> + +Breaks the binding between a variable and a package. +(See L<tie|/tie VARIABLE,CLASSNAME,LIST>.) +Has no effect if the variable is not tied. + +=item unshift ARRAY,LIST +X<unshift> + +=item unshift EXPR,LIST + +Does the opposite of a C<shift>. Or the opposite of a C<push>, +depending on how you look at it. Prepends list to the front of the +array and returns the new number of elements in the array. + + unshift(@ARGV, '-e') unless $ARGV[0] =~ /^-/; + +Note the LIST is prepended whole, not one element at a time, so the +prepended elements stay in the same order. Use C<reverse> to do the +reverse. + +Starting with Perl 5.14, C<unshift> can take a scalar EXPR, which must hold +a reference to an unblessed array. The argument will be dereferenced +automatically. This aspect of C<unshift> is considered highly +experimental. The exact behaviour may change in a future version of Perl. + +=item use Module VERSION LIST +X<use> X<module> X<import> + +=item use Module VERSION + +=item use Module LIST + +=item use Module + +=item use VERSION + +Imports some semantics into the current package from the named module, +generally by aliasing certain subroutine or variable names into your +package. It is exactly equivalent to + + BEGIN { require Module; Module->import( LIST ); } + +except that Module I<must> be a bareword. +The importation can be made conditional; see L<if>. + +In the peculiar C<use VERSION> form, VERSION may be either a positive +decimal fraction such as 5.006, which will be compared to C<$]>, or a v-string +of the form v5.6.1, which will be compared to C<$^V> (aka $PERL_VERSION). An +exception is raised if VERSION is greater than the version of the +current Perl interpreter; Perl will not attempt to parse the rest of the +file. Compare with L</require>, which can do a similar check at run time. +Symmetrically, C<no VERSION> allows you to specify that you want a version +of Perl older than the specified one. + +Specifying VERSION as a literal of the form v5.6.1 should generally be +avoided, because it leads to misleading error messages under earlier +versions of Perl (that is, prior to 5.6.0) that do not support this +syntax. The equivalent numeric version should be used instead. + + use v5.6.1; # compile time version check + use 5.6.1; # ditto + use 5.006_001; # ditto; preferred for backwards compatibility + +This is often useful if you need to check the current Perl version before +C<use>ing library modules that won't work with older versions of Perl. +(We try not to do this more than we have to.) + +Also, if the specified Perl version is greater than or equal to 5.9.5, +C<use VERSION> will also load the C<feature> pragma and enable all +features available in the requested version. See L<feature>. +Similarly, if the specified Perl version is greater than or equal to +5.11.0, strictures are enabled lexically as with C<use strict> (except +that the F<strict.pm> file is not actually loaded). + +The C<BEGIN> forces the C<require> and C<import> to happen at compile time. The +C<require> makes sure the module is loaded into memory if it hasn't been +yet. The C<import> is not a builtin; it's just an ordinary static method +call into the C<Module> package to tell the module to import the list of +features back into the current package. The module can implement its +C<import> method any way it likes, though most modules just choose to +derive their C<import> method via inheritance from the C<Exporter> class that +is defined in the C<Exporter> module. See L<Exporter>. If no C<import> +method can be found then the call is skipped, even if there is an AUTOLOAD +method. + +If you do not want to call the package's C<import> method (for instance, +to stop your namespace from being altered), explicitly supply the empty list: + + use Module (); + +That is exactly equivalent to + + BEGIN { require Module } + +If the VERSION argument is present between Module and LIST, then the +C<use> will call the VERSION method in class Module with the given +version as an argument. The default VERSION method, inherited from +the UNIVERSAL class, croaks if the given version is larger than the +value of the variable C<$Module::VERSION>. + +Again, there is a distinction between omitting LIST (C<import> called +with no arguments) and an explicit empty LIST C<()> (C<import> not +called). Note that there is no comma after VERSION! + +Because this is a wide-open interface, pragmas (compiler directives) +are also implemented this way. Currently implemented pragmas are: + + use constant; + use diagnostics; + use integer; + use sigtrap qw(SEGV BUS); + use strict qw(subs vars refs); + use subs qw(afunc blurfl); + use warnings qw(all); + use sort qw(stable _quicksort _mergesort); + +Some of these pseudo-modules import semantics into the current +block scope (like C<strict> or C<integer>, unlike ordinary modules, +which import symbols into the current package (which are effective +through the end of the file). + +Because C<use> takes effect at compile time, it doesn't respect the +ordinary flow control of the code being compiled. In particular, putting +a C<use> inside the false branch of a conditional doesn't prevent it +from being processed. If a module or pragma only needs to be loaded +conditionally, this can be done using the L<if> pragma: + + use if $] < 5.008, "utf8"; + use if WANT_WARNINGS, warnings => qw(all); + +There's a corresponding C<no> declaration that unimports meanings imported +by C<use>, i.e., it calls C<unimport Module LIST> instead of C<import>. +It behaves just as C<import> does with VERSION, an omitted or empty LIST, +or no unimport method being found. + + no integer; + no strict 'refs'; + no warnings; + +Care should be taken when using the C<no VERSION> form of C<no>. It is +I<only> meant to be used to assert that the running Perl is of a earlier +version than its argument and I<not> to undo the feature-enabling side effects +of C<use VERSION>. + +See L<perlmodlib> for a list of standard modules and pragmas. See L<perlrun> +for the C<-M> and C<-m> command-line options to Perl that give C<use> +functionality from the command-line. + +=item utime LIST +X<utime> + +Changes the access and modification times on each file of a list of +files. The first two elements of the list must be the NUMERIC access +and modification times, in that order. Returns the number of files +successfully changed. The inode change time of each file is set +to the current time. For example, this code has the same effect as the +Unix touch(1) command when the files I<already exist> and belong to +the user running the program: + + #!/usr/bin/perl + $atime = $mtime = time; + utime $atime, $mtime, @ARGV; + +Since Perl 5.7.2, if the first two elements of the list are C<undef>, +the utime(2) syscall from your C library is called with a null second +argument. On most systems, this will set the file's access and +modification times to the current time (i.e., equivalent to the example +above) and will work even on files you don't own provided you have write +permission: + + for $file (@ARGV) { + utime(undef, undef, $file) + || warn "couldn't touch $file: $!"; + } + +Under NFS this will use the time of the NFS server, not the time of +the local machine. If there is a time synchronization problem, the +NFS server and local machine will have different times. The Unix +touch(1) command will in fact normally use this form instead of the +one shown in the first example. + +Passing only one of the first two elements as C<undef> is +equivalent to passing a 0 and will not have the effect +described when both are C<undef>. This also triggers an +uninitialized warning. + +On systems that support futimes(2), you may pass filehandles among the +files. On systems that don't support futimes(2), passing filehandles raises +an exception. Filehandles must be passed as globs or glob references to be +recognized; barewords are considered filenames. + +Portability issues: L<perlport/utime>. + +=item values HASH +X<values> + +=item values ARRAY + +=item values EXPR + +Returns a list consisting of all the values of the named hash, or the values +of an array. (In scalar context, returns the number of values.) + +The values are returned in an apparently random order. The actual +random order is subject to change in future versions of Perl, but it +is guaranteed to be the same order as either the C<keys> or C<each> +function would produce on the same (unmodified) hash. Since Perl +5.8.1 the ordering is different even between different runs of Perl +for security reasons (see L<perlsec/"Algorithmic Complexity Attacks">). + +As a side effect, calling values() resets the HASH or ARRAY's internal +iterator; +see L</each>. (In particular, calling values() in void context resets +the iterator with no other overhead. Apart from resetting the iterator, +C<values @array> in list context is the same as plain C<@array>. +We recommend that you use void context C<keys @array> for this, but reasoned +that it taking C<values @array> out would require more documentation than +leaving it in.) + +Note that the values are not copied, which means modifying them will +modify the contents of the hash: + + for (values %hash) { s/foo/bar/g } # modifies %hash values + for (@hash{keys %hash}) { s/foo/bar/g } # same + +Starting with Perl 5.14, C<values> can take a scalar EXPR, which must hold +a reference to an unblessed hash or array. The argument will be +dereferenced automatically. This aspect of C<values> is considered highly +experimental. The exact behaviour may change in a future version of Perl. + + for (values $hashref) { ... } + for (values $obj->get_arrayref) { ... } + +See also C<keys>, C<each>, and C<sort>. + +=item vec EXPR,OFFSET,BITS +X<vec> X<bit> X<bit vector> + +Treats the string in EXPR as a bit vector made up of elements of +width BITS and returns the value of the element specified by OFFSET +as an unsigned integer. BITS therefore specifies the number of bits +that are reserved for each element in the bit vector. This must +be a power of two from 1 to 32 (or 64, if your platform supports +that). + +If BITS is 8, "elements" coincide with bytes of the input string. + +If BITS is 16 or more, bytes of the input string are grouped into chunks +of size BITS/8, and each group is converted to a number as with +pack()/unpack() with big-endian formats C<n>/C<N> (and analogously +for BITS==64). See L<"pack"> for details. + +If bits is 4 or less, the string is broken into bytes, then the bits +of each byte are broken into 8/BITS groups. Bits of a byte are +numbered in a little-endian-ish way, as in C<0x01>, C<0x02>, +C<0x04>, C<0x08>, C<0x10>, C<0x20>, C<0x40>, C<0x80>. For example, +breaking the single input byte C<chr(0x36)> into two groups gives a list +C<(0x6, 0x3)>; breaking it into 4 groups gives C<(0x2, 0x1, 0x3, 0x0)>. + +C<vec> may also be assigned to, in which case parentheses are needed +to give the expression the correct precedence as in + + vec($image, $max_x * $x + $y, 8) = 3; + +If the selected element is outside the string, the value 0 is returned. +If an element off the end of the string is written to, Perl will first +extend the string with sufficiently many zero bytes. It is an error +to try to write off the beginning of the string (i.e., negative OFFSET). + +If the string happens to be encoded as UTF-8 internally (and thus has +the UTF8 flag set), this is ignored by C<vec>, and it operates on the +internal byte string, not the conceptual character string, even if you +only have characters with values less than 256. + +Strings created with C<vec> can also be manipulated with the logical +operators C<|>, C<&>, C<^>, and C<~>. These operators will assume a bit +vector operation is desired when both operands are strings. +See L<perlop/"Bitwise String Operators">. + +The following code will build up an ASCII string saying C<'PerlPerlPerl'>. +The comments show the string after each step. Note that this code works +in the same way on big-endian or little-endian machines. + + my $foo = ''; + vec($foo, 0, 32) = 0x5065726C; # 'Perl' + + # $foo eq "Perl" eq "\x50\x65\x72\x6C", 32 bits + print vec($foo, 0, 8); # prints 80 == 0x50 == ord('P') + + vec($foo, 2, 16) = 0x5065; # 'PerlPe' + vec($foo, 3, 16) = 0x726C; # 'PerlPerl' + vec($foo, 8, 8) = 0x50; # 'PerlPerlP' + vec($foo, 9, 8) = 0x65; # 'PerlPerlPe' + vec($foo, 20, 4) = 2; # 'PerlPerlPe' . "\x02" + vec($foo, 21, 4) = 7; # 'PerlPerlPer' + # 'r' is "\x72" + vec($foo, 45, 2) = 3; # 'PerlPerlPer' . "\x0c" + vec($foo, 93, 1) = 1; # 'PerlPerlPer' . "\x2c" + vec($foo, 94, 1) = 1; # 'PerlPerlPerl' + # 'l' is "\x6c" + +To transform a bit vector into a string or list of 0's and 1's, use these: + + $bits = unpack("b*", $vector); + @bits = split(//, unpack("b*", $vector)); + +If you know the exact length in bits, it can be used in place of the C<*>. + +Here is an example to illustrate how the bits actually fall in place: + + #!/usr/bin/perl -wl + + print <<'EOT'; + 0 1 2 3 + unpack("V",$_) 01234567890123456789012345678901 + ------------------------------------------------------------------ + EOT + + for $w (0..3) { + $width = 2**$w; + for ($shift=0; $shift < $width; ++$shift) { + for ($off=0; $off < 32/$width; ++$off) { + $str = pack("B*", "0"x32); + $bits = (1<<$shift); + vec($str, $off, $width) = $bits; + $res = unpack("b*",$str); + $val = unpack("V", $str); + write; + } + } + } + + format STDOUT = + vec($_,@#,@#) = @<< == @######### @>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> + $off, $width, $bits, $val, $res + . + __END__ + +Regardless of the machine architecture on which it runs, the +example above should print the following table: + + 0 1 2 3 + unpack("V",$_) 01234567890123456789012345678901 + ------------------------------------------------------------------ + vec($_, 0, 1) = 1 == 1 10000000000000000000000000000000 + vec($_, 1, 1) = 1 == 2 01000000000000000000000000000000 + vec($_, 2, 1) = 1 == 4 00100000000000000000000000000000 + vec($_, 3, 1) = 1 == 8 00010000000000000000000000000000 + vec($_, 4, 1) = 1 == 16 00001000000000000000000000000000 + vec($_, 5, 1) = 1 == 32 00000100000000000000000000000000 + vec($_, 6, 1) = 1 == 64 00000010000000000000000000000000 + vec($_, 7, 1) = 1 == 128 00000001000000000000000000000000 + vec($_, 8, 1) = 1 == 256 00000000100000000000000000000000 + vec($_, 9, 1) = 1 == 512 00000000010000000000000000000000 + vec($_,10, 1) = 1 == 1024 00000000001000000000000000000000 + vec($_,11, 1) = 1 == 2048 00000000000100000000000000000000 + vec($_,12, 1) = 1 == 4096 00000000000010000000000000000000 + vec($_,13, 1) = 1 == 8192 00000000000001000000000000000000 + vec($_,14, 1) = 1 == 16384 00000000000000100000000000000000 + vec($_,15, 1) = 1 == 32768 00000000000000010000000000000000 + vec($_,16, 1) = 1 == 65536 00000000000000001000000000000000 + vec($_,17, 1) = 1 == 131072 00000000000000000100000000000000 + vec($_,18, 1) = 1 == 262144 00000000000000000010000000000000 + vec($_,19, 1) = 1 == 524288 00000000000000000001000000000000 + vec($_,20, 1) = 1 == 1048576 00000000000000000000100000000000 + vec($_,21, 1) = 1 == 2097152 00000000000000000000010000000000 + vec($_,22, 1) = 1 == 4194304 00000000000000000000001000000000 + vec($_,23, 1) = 1 == 8388608 00000000000000000000000100000000 + vec($_,24, 1) = 1 == 16777216 00000000000000000000000010000000 + vec($_,25, 1) = 1 == 33554432 00000000000000000000000001000000 + vec($_,26, 1) = 1 == 67108864 00000000000000000000000000100000 + vec($_,27, 1) = 1 == 134217728 00000000000000000000000000010000 + vec($_,28, 1) = 1 == 268435456 00000000000000000000000000001000 + vec($_,29, 1) = 1 == 536870912 00000000000000000000000000000100 + vec($_,30, 1) = 1 == 1073741824 00000000000000000000000000000010 + vec($_,31, 1) = 1 == 2147483648 00000000000000000000000000000001 + vec($_, 0, 2) = 1 == 1 10000000000000000000000000000000 + vec($_, 1, 2) = 1 == 4 00100000000000000000000000000000 + vec($_, 2, 2) = 1 == 16 00001000000000000000000000000000 + vec($_, 3, 2) = 1 == 64 00000010000000000000000000000000 + vec($_, 4, 2) = 1 == 256 00000000100000000000000000000000 + vec($_, 5, 2) = 1 == 1024 00000000001000000000000000000000 + vec($_, 6, 2) = 1 == 4096 00000000000010000000000000000000 + vec($_, 7, 2) = 1 == 16384 00000000000000100000000000000000 + vec($_, 8, 2) = 1 == 65536 00000000000000001000000000000000 + vec($_, 9, 2) = 1 == 262144 00000000000000000010000000000000 + vec($_,10, 2) = 1 == 1048576 00000000000000000000100000000000 + vec($_,11, 2) = 1 == 4194304 00000000000000000000001000000000 + vec($_,12, 2) = 1 == 16777216 00000000000000000000000010000000 + vec($_,13, 2) = 1 == 67108864 00000000000000000000000000100000 + vec($_,14, 2) = 1 == 268435456 00000000000000000000000000001000 + vec($_,15, 2) = 1 == 1073741824 00000000000000000000000000000010 + vec($_, 0, 2) = 2 == 2 01000000000000000000000000000000 + vec($_, 1, 2) = 2 == 8 00010000000000000000000000000000 + vec($_, 2, 2) = 2 == 32 00000100000000000000000000000000 + vec($_, 3, 2) = 2 == 128 00000001000000000000000000000000 + vec($_, 4, 2) = 2 == 512 00000000010000000000000000000000 + vec($_, 5, 2) = 2 == 2048 00000000000100000000000000000000 + vec($_, 6, 2) = 2 == 8192 00000000000001000000000000000000 + vec($_, 7, 2) = 2 == 32768 00000000000000010000000000000000 + vec($_, 8, 2) = 2 == 131072 00000000000000000100000000000000 + vec($_, 9, 2) = 2 == 524288 00000000000000000001000000000000 + vec($_,10, 2) = 2 == 2097152 00000000000000000000010000000000 + vec($_,11, 2) = 2 == 8388608 00000000000000000000000100000000 + vec($_,12, 2) = 2 == 33554432 00000000000000000000000001000000 + vec($_,13, 2) = 2 == 134217728 00000000000000000000000000010000 + vec($_,14, 2) = 2 == 536870912 00000000000000000000000000000100 + vec($_,15, 2) = 2 == 2147483648 00000000000000000000000000000001 + vec($_, 0, 4) = 1 == 1 10000000000000000000000000000000 + vec($_, 1, 4) = 1 == 16 00001000000000000000000000000000 + vec($_, 2, 4) = 1 == 256 00000000100000000000000000000000 + vec($_, 3, 4) = 1 == 4096 00000000000010000000000000000000 + vec($_, 4, 4) = 1 == 65536 00000000000000001000000000000000 + vec($_, 5, 4) = 1 == 1048576 00000000000000000000100000000000 + vec($_, 6, 4) = 1 == 16777216 00000000000000000000000010000000 + vec($_, 7, 4) = 1 == 268435456 00000000000000000000000000001000 + vec($_, 0, 4) = 2 == 2 01000000000000000000000000000000 + vec($_, 1, 4) = 2 == 32 00000100000000000000000000000000 + vec($_, 2, 4) = 2 == 512 00000000010000000000000000000000 + vec($_, 3, 4) = 2 == 8192 00000000000001000000000000000000 + vec($_, 4, 4) = 2 == 131072 00000000000000000100000000000000 + vec($_, 5, 4) = 2 == 2097152 00000000000000000000010000000000 + vec($_, 6, 4) = 2 == 33554432 00000000000000000000000001000000 + vec($_, 7, 4) = 2 == 536870912 00000000000000000000000000000100 + vec($_, 0, 4) = 4 == 4 00100000000000000000000000000000 + vec($_, 1, 4) = 4 == 64 00000010000000000000000000000000 + vec($_, 2, 4) = 4 == 1024 00000000001000000000000000000000 + vec($_, 3, 4) = 4 == 16384 00000000000000100000000000000000 + vec($_, 4, 4) = 4 == 262144 00000000000000000010000000000000 + vec($_, 5, 4) = 4 == 4194304 00000000000000000000001000000000 + vec($_, 6, 4) = 4 == 67108864 00000000000000000000000000100000 + vec($_, 7, 4) = 4 == 1073741824 00000000000000000000000000000010 + vec($_, 0, 4) = 8 == 8 00010000000000000000000000000000 + vec($_, 1, 4) = 8 == 128 00000001000000000000000000000000 + vec($_, 2, 4) = 8 == 2048 00000000000100000000000000000000 + vec($_, 3, 4) = 8 == 32768 00000000000000010000000000000000 + vec($_, 4, 4) = 8 == 524288 00000000000000000001000000000000 + vec($_, 5, 4) = 8 == 8388608 00000000000000000000000100000000 + vec($_, 6, 4) = 8 == 134217728 00000000000000000000000000010000 + vec($_, 7, 4) = 8 == 2147483648 00000000000000000000000000000001 + vec($_, 0, 8) = 1 == 1 10000000000000000000000000000000 + vec($_, 1, 8) = 1 == 256 00000000100000000000000000000000 + vec($_, 2, 8) = 1 == 65536 00000000000000001000000000000000 + vec($_, 3, 8) = 1 == 16777216 00000000000000000000000010000000 + vec($_, 0, 8) = 2 == 2 01000000000000000000000000000000 + vec($_, 1, 8) = 2 == 512 00000000010000000000000000000000 + vec($_, 2, 8) = 2 == 131072 00000000000000000100000000000000 + vec($_, 3, 8) = 2 == 33554432 00000000000000000000000001000000 + vec($_, 0, 8) = 4 == 4 00100000000000000000000000000000 + vec($_, 1, 8) = 4 == 1024 00000000001000000000000000000000 + vec($_, 2, 8) = 4 == 262144 00000000000000000010000000000000 + vec($_, 3, 8) = 4 == 67108864 00000000000000000000000000100000 + vec($_, 0, 8) = 8 == 8 00010000000000000000000000000000 + vec($_, 1, 8) = 8 == 2048 00000000000100000000000000000000 + vec($_, 2, 8) = 8 == 524288 00000000000000000001000000000000 + vec($_, 3, 8) = 8 == 134217728 00000000000000000000000000010000 + vec($_, 0, 8) = 16 == 16 00001000000000000000000000000000 + vec($_, 1, 8) = 16 == 4096 00000000000010000000000000000000 + vec($_, 2, 8) = 16 == 1048576 00000000000000000000100000000000 + vec($_, 3, 8) = 16 == 268435456 00000000000000000000000000001000 + vec($_, 0, 8) = 32 == 32 00000100000000000000000000000000 + vec($_, 1, 8) = 32 == 8192 00000000000001000000000000000000 + vec($_, 2, 8) = 32 == 2097152 00000000000000000000010000000000 + vec($_, 3, 8) = 32 == 536870912 00000000000000000000000000000100 + vec($_, 0, 8) = 64 == 64 00000010000000000000000000000000 + vec($_, 1, 8) = 64 == 16384 00000000000000100000000000000000 + vec($_, 2, 8) = 64 == 4194304 00000000000000000000001000000000 + vec($_, 3, 8) = 64 == 1073741824 00000000000000000000000000000010 + vec($_, 0, 8) = 128 == 128 00000001000000000000000000000000 + vec($_, 1, 8) = 128 == 32768 00000000000000010000000000000000 + vec($_, 2, 8) = 128 == 8388608 00000000000000000000000100000000 + vec($_, 3, 8) = 128 == 2147483648 00000000000000000000000000000001 + +=item wait +X<wait> + +Behaves like wait(2) on your system: it waits for a child +process to terminate and returns the pid of the deceased process, or +C<-1> if there are no child processes. The status is returned in C<$?> +and C<${^CHILD_ERROR_NATIVE}>. +Note that a return value of C<-1> could mean that child processes are +being automatically reaped, as described in L<perlipc>. + +If you use wait in your handler for $SIG{CHLD} it may accidentally for the +child created by qx() or system(). See L<perlipc> for details. + +Portability issues: L<perlport/wait>. + +=item waitpid PID,FLAGS +X<waitpid> + +Waits for a particular child process to terminate and returns the pid of +the deceased process, or C<-1> if there is no such child process. On some +systems, a value of 0 indicates that there are processes still running. +The status is returned in C<$?> and C<${^CHILD_ERROR_NATIVE}>. If you say + + use POSIX ":sys_wait_h"; + #... + do { + $kid = waitpid(-1, WNOHANG); + } while $kid > 0; + +then you can do a non-blocking wait for all pending zombie processes. +Non-blocking wait is available on machines supporting either the +waitpid(2) or wait4(2) syscalls. However, waiting for a particular +pid with FLAGS of C<0> is implemented everywhere. (Perl emulates the +system call by remembering the status values of processes that have +exited but have not been harvested by the Perl script yet.) + +Note that on some systems, a return value of C<-1> could mean that child +processes are being automatically reaped. See L<perlipc> for details, +and for other examples. + +Portability issues: L<perlport/waitpid>. + +=item wantarray +X<wantarray> X<context> + +Returns true if the context of the currently executing subroutine or +C<eval> is looking for a list value. Returns false if the context is +looking for a scalar. Returns the undefined value if the context is +looking for no value (void context). + + return unless defined wantarray; # don't bother doing more + my @a = complex_calculation(); + return wantarray ? @a : "@a"; + +C<wantarray()>'s result is unspecified in the top level of a file, +in a C<BEGIN>, C<UNITCHECK>, C<CHECK>, C<INIT> or C<END> block, or +in a C<DESTROY> method. + +This function should have been named wantlist() instead. + +=item warn LIST +X<warn> X<warning> X<STDERR> + +Prints the value of LIST to STDERR. If the last element of LIST does +not end in a newline, it appends the same file/line number text as C<die> +does. + +If the output is empty and C<$@> already contains a value (typically from a +previous eval) that value is used after appending C<"\t...caught"> +to C<$@>. This is useful for staying almost, but not entirely similar to +C<die>. + +If C<$@> is empty then the string C<"Warning: Something's wrong"> is used. + +No message is printed if there is a C<$SIG{__WARN__}> handler +installed. It is the handler's responsibility to deal with the message +as it sees fit (like, for instance, converting it into a C<die>). Most +handlers must therefore arrange to actually display the +warnings that they are not prepared to deal with, by calling C<warn> +again in the handler. Note that this is quite safe and will not +produce an endless loop, since C<__WARN__> hooks are not called from +inside one. + +You will find this behavior is slightly different from that of +C<$SIG{__DIE__}> handlers (which don't suppress the error text, but can +instead call C<die> again to change it). + +Using a C<__WARN__> handler provides a powerful way to silence all +warnings (even the so-called mandatory ones). An example: + + # wipe out *all* compile-time warnings + BEGIN { $SIG{'__WARN__'} = sub { warn $_[0] if $DOWARN } } + my $foo = 10; + my $foo = 20; # no warning about duplicate my $foo, + # but hey, you asked for it! + # no compile-time or run-time warnings before here + $DOWARN = 1; + + # run-time warnings enabled after here + warn "\$foo is alive and $foo!"; # does show up + +See L<perlvar> for details on setting C<%SIG> entries and for more +examples. See the Carp module for other kinds of warnings using its +carp() and cluck() functions. + +=item when EXPR BLOCK +X<when> + +=item when BLOCK + +C<when> is analogous to the C<case> keyword in other languages. Used with a +C<foreach> loop or the experimental C<given> block, C<when> can be used in +Perl to implement C<switch>/C<case> like statements. Available as a +statement after Perl 5.10 and as a statement modifier after 5.14. +Here are three examples: + + use v5.10; + foreach (@fruits) { + when (/apples?/) { + say "I like apples." + } + when (/oranges?/) { + say "I don't like oranges." + } + default { + say "I don't like anything" + } + } + + # require 5.14 for when as statement modifier + use v5.14; + foreach (@fruits) { + say "I like apples." when /apples?/; + say "I don't like oranges." when /oranges?; + default { say "I don't like anything" } + } + + use v5.10; + given ($fruit) { + when (/apples?/) { + say "I like apples." + } + when (/oranges?/) { + say "I don't like oranges." + } + default { + say "I don't like anything" + } + } + +See L<perlsyn/"Switch statements"> for detailed information. + +=item write FILEHANDLE +X<write> + +=item write EXPR + +=item write + +Writes a formatted record (possibly multi-line) to the specified FILEHANDLE, +using the format associated with that file. By default the format for +a file is the one having the same name as the filehandle, but the +format for the current output channel (see the C<select> function) may be set +explicitly by assigning the name of the format to the C<$~> variable. + +Top of form processing is handled automatically: if there is insufficient +room on the current page for the formatted record, the page is advanced by +writing a form feed, a special top-of-page format is used to format the new +page header before the record is written. By default, the top-of-page +format is the name of the filehandle with "_TOP" appended. This would be a +problem with autovivified filehandles, but it may be dynamically set to the +format of your choice by assigning the name to the C<$^> variable while +that filehandle is selected. The number of lines remaining on the current +page is in variable C<$->, which can be set to C<0> to force a new page. + +If FILEHANDLE is unspecified, output goes to the current default output +channel, which starts out as STDOUT but may be changed by the +C<select> operator. If the FILEHANDLE is an EXPR, then the expression +is evaluated and the resulting string is used to look up the name of +the FILEHANDLE at run time. For more on formats, see L<perlform>. + +Note that write is I<not> the opposite of C<read>. Unfortunately. + +=item y/// + +The transliteration operator. Same as C<tr///>. See +L<perlop/"Quote and Quote-like Operators">. + +=back + +=cut diff --git a/dist/Pod-Perldoc/corpus/utf8.pod b/dist/Pod-Perldoc/corpus/utf8.pod new file mode 100644 index 0000000000..0c12b7e2a2 --- /dev/null +++ b/dist/Pod-Perldoc/corpus/utf8.pod @@ -0,0 +1,13 @@ +=encoding utf8 + +=head1 NAME + +Büster is my cat + +=head1 DESCRIPTION + +Ingy döt Net is a Perl programmer + +The Roman number for 5 is â…¤ + +=cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc.pm index 90aaff2559..3de1cd65f4 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc.pm @@ -1,18 +1,19 @@ +use 5.006; # we use some open(X, "<", $y) syntax -require 5; -use 5.006; # we use some open(X, "<", $y) syntax package Pod::Perldoc; use strict; use warnings; use Config '%Config'; use Fcntl; # for sysopen +use File::Basename qw(basename); use File::Spec::Functions qw(catfile catdir splitdir); use vars qw($VERSION @Pagers $Bindir $Pod2man $Temp_Files_Created $Temp_File_Lifetime ); -$VERSION = '3.15_08'; +$VERSION = '3.15_15'; + #.......................................................................... BEGIN { # Make a DEBUG constant very first thing... @@ -27,6 +28,20 @@ BEGIN { # Make a DEBUG constant very first thing... } use Pod::Perldoc::GetOptsOO; # uses the DEBUG. +use Carp qw(croak carp); + +# these are also in BaseTo, which I don't want to inherit +sub warn { + my( $self, @messages ) = @_; + + carp( join "\n", @messages, '' ); + } + +sub die { + my( $self, @messages ) = @_; + + croak( join "\n", @messages, '' ); + } #.......................................................................... @@ -35,13 +50,13 @@ sub FALSE () {return} sub BE_LENIENT () {1} BEGIN { - *IS_VMS = $^O eq 'VMS' ? \&TRUE : \&FALSE unless defined &IS_VMS; - *IS_MSWin32 = $^O eq 'MSWin32' ? \&TRUE : \&FALSE unless defined &IS_MSWin32; - *IS_Dos = $^O eq 'dos' ? \&TRUE : \&FALSE unless defined &IS_Dos; - *IS_OS2 = $^O eq 'os2' ? \&TRUE : \&FALSE unless defined &IS_OS2; - *IS_Cygwin = $^O eq 'cygwin' ? \&TRUE : \&FALSE unless defined &IS_Cygwin; - *IS_Linux = $^O eq 'linux' ? \&TRUE : \&FALSE unless defined &IS_Linux; - *IS_HPUX = $^O =~ m/hpux/ ? \&TRUE : \&FALSE unless defined &IS_HPUX; + *is_vms = $^O eq 'VMS' ? \&TRUE : \&FALSE unless defined &is_vms; + *is_mswin32 = $^O eq 'MSWin32' ? \&TRUE : \&FALSE unless defined &is_mswin32; + *is_dos = $^O eq 'dos' ? \&TRUE : \&FALSE unless defined &is_dos; + *is_os2 = $^O eq 'os2' ? \&TRUE : \&FALSE unless defined &is_os2; + *is_cygwin = $^O eq 'cygwin' ? \&TRUE : \&FALSE unless defined &is_cygwin; + *is_linux = $^O eq 'linux' ? \&TRUE : \&FALSE unless defined &is_linux; + *is_hpux = $^O =~ m/hpux/ ? \&TRUE : \&FALSE unless defined &is_hpux; } $Temp_File_Lifetime ||= 60 * 60 * 24 * 5; @@ -52,7 +67,7 @@ $Temp_File_Lifetime ||= 60 * 60 * 24 * 5; #.......................................................................... { my $pager = $Config{'pager'}; - push @Pagers, $pager if -x (split /\s+/, $pager)[0] or IS_VMS; + push @Pagers, $pager if -x (split /\s+/, $pager)[0] or __PACKAGE__->is_vms; } $Bindir = $Config{'scriptdirexp'}; $Pod2man = "pod2man" . ( $Config{'versiononly'} ? $Config{'version'} : '' ); @@ -83,7 +98,7 @@ sub opt_w_with { # Specify an option for the formatter subclass $option =~ tr/\-/_/s; # tolerate "foo-bar" for "foo_bar" $self->add_formatter_option( $option, $option_value ); } else { - warn "\"$value\" isn't a good formatter option name. I'm ignoring it!\n"; + $self->warn( qq("$value" isn't a good formatter option name. I'm ignoring it!\n ) ); } return; } @@ -99,17 +114,17 @@ sub opt_M_with { # specify formatter class name(s) # A mildly restrictive concept of what modulenames are valid. push @classes_to_add, $1; # untaint } else { - warn "\"$classname\" isn't a valid classname. Ignoring.\n"; + $self->warn( qq("$classname" isn't a valid classname. Ignoring.\n) ); } } - + unshift @{ $self->{'formatter_classes'} }, @classes_to_add; - + DEBUG > 3 and print( "Adding @classes_to_add to the list of formatter classes, " . "making them @{ $self->{'formatter_classes'} }.\n" ); - + return; } @@ -119,9 +134,9 @@ sub opt_V { # report version and exit (defined(&Win32::BuildNumber) and defined &Win32::BuildNumber()) ? (" (win32 build ", &Win32::BuildNumber(), ")") : (), - + (chr(65) eq 'A') ? () : " (non-ASCII)", - + "\n", ; exit; @@ -152,14 +167,14 @@ sub opt_o_with { # "o" for output format if($rest =~ m/^(\w+)$/s) { $rest = $1; #untaint } else { - warn "\"$rest\" isn't a valid output format. Skipping.\n"; + $self->warn( qq("$rest" isn't a valid output format. Skipping.\n") ); return; } - + $self->aside("Noting \"$rest\" as desired output format...\n"); - + # Figure out what class(es) that could actually mean... - + my @classes; foreach my $prefix ("Pod::Perldoc::To", "Pod::Simple::", "Pod::") { # Messy but smart: @@ -168,10 +183,10 @@ sub opt_o_with { # "o" for output format "\L$rest", "\L\u$rest", "\U$rest" # And then try variations ) { + $self->aside("Considering $prefix$stem\n"); push @classes, $prefix . $stem; - #print "Considering $prefix$stem\n"; } - + # Tidier, but misses too much: #push @classes, $prefix . ucfirst(lc($rest)); } @@ -233,12 +248,12 @@ sub aside { # If we're in -D or DEBUG mode, say this. sub usage { my $self = shift; - warn "@_\n" if @_; - + $self->warn( "@_\n" ) if @_; + # Erase evidence of previous errors (if any), so exit status is simple. $! = 0; - - die <<EOF; + + $self->die( <<EOF ); perldoc [options] PageName|ModuleName|ProgramName|URL... perldoc [options] -f BuiltinFunction perldoc [options] -q FAQRegex @@ -249,11 +264,11 @@ Options: -V Report version -r Recursive search (slow) -i Ignore case - -t Display pod using pod2text instead of pod2man and nroff + -t Display pod using pod2text instead of Pod::Man and groff (-t is the default on win32 unless -n is specified) -u Display unformatted pod text -m Display module's file in its entirety - -n Specify replacement for nroff + -n Specify replacement for groff -l Display the module's file name -F Arguments are file names, not modules -D Verbosely describe what's going on @@ -271,13 +286,13 @@ Options: PageName|ModuleName|ProgramName|URL... is the name of a piece of documentation that you want to look at. You may either give a descriptive name of the page (as in the case of - 'perlfunc') the name of a module, either like 'Term::Info' or like - 'Term/Info', or the name of a program, like 'perldoc', or a URL - starting with http(s). + `perlfunc') the name of a module, either like `Term::Info' or like + `Term/Info', or the name of a program, like `perldoc', or a URL + starting with http(s). BuiltinFunction is the name of a perl function. Will extract documentation from - 'perlfunc'. + `perlfunc' or `perlop'. FAQRegex is a regex. Will search perlfaq[1-9] for and extract any @@ -294,26 +309,85 @@ EOF #.......................................................................... sub program_name { - my $me = $0; # Editing $0 is unportable + my( $self ) = @_; + + if( my $link = readlink( $0 ) ) { + $self->debug( "The value in $0 is a symbolic link to $link\n" ); + } + + my $basename = basename( $0 ); - $me =~ s,.*[/\\],,; # get basename + $self->debug( "\$0 is [$0]\nbasename is [$basename]\n" ); + # possible name forms + # perldoc + # perldoc-v5.14 + # perldoc-5.14 + # perldoc-5.14.2 + # perlvar # an alias mentioned in Camel 3 + { + my( $untainted ) = $basename =~ m/( + \A + perl + (?: + doc | func | faq | help | op | toc | var # Camel 3 + ) + (?: -? v? \d+ \. \d+ (?:\. \d+)? ) # possible version + (?: \. (?: bat | exe | com ) )? # possible extension + \z + ) + /x; + + return $untainted if $untainted; + } + + $self->warn(<<"HERE"); +You called the perldoc command with a name that I didn't recognize. +This might mean that someone is tricking you into running a +program you don't intend to use, but it also might mean that you +created your own link to perldoc. I think your program name is +[$basename]. + +I'll allow this if the filename looks only has [a-zA-Z0-9._-]. +HERE + + { + my( $untainted ) = $basename =~ m/( + \A [a-zA-Z0-9._-]+ \z + )/x; - return $me; + return $untainted if $untainted; + } + + $self->die(<<"HERE"); +I think that your name for perldoc is potentially unsafe, so I'm +going to disallow it. I'd rather you be safe than sorry. If you +intended to use the name I'm disallowing, please tell the maintainers +about it. Write to: + + Pod-Perldoc\@rt.cpan.org + +HERE } #.......................................................................... sub usage_brief { my $self = shift; - my $me = $self->program_name; + my $program_name = $self->program_name; - die <<"EOUSAGE"; -Usage: $me [-h] [-V] [-r] [-i] [-D] [-t] [-u] [-m] [-n nroffer_program] [-l] [-T] [-d output_filename] [-o output_format] [-M FormatterModuleNameToUse] [-w formatter_option:option_value] [-L translation_code] [-F] [-X] PageName|ModuleName|ProgramName - $me -f PerlFunc - $me -q FAQKeywords - $me -v PerlVar + $self->die( <<"EOUSAGE" ); +Usage: $program_name [-hVriDtumFXlT] [-n nroffer_program] + [-d output_filename] [-o output_format] [-M FormatterModule] + [-w formatter_option:option_value] [-L translation_code] + PageName|ModuleName|ProgramName -The -h option prints more help. Also try "$me perldoc" to get +Examples: + + $program_name -f PerlFunc + $program_name -q FAQKeywords + $program_name -v PerlVar + +The -h option prints more help. Also try "$program_name perldoc" to get acquainted with the system. [Perldoc v$VERSION] EOUSAGE @@ -321,7 +395,7 @@ EOUSAGE #.......................................................................... -sub pagers { @{ shift->{'pagers'} } } +sub pagers { @{ shift->{'pagers'} } } #.......................................................................... @@ -345,8 +419,8 @@ sub init { $self->{'args'} ||= \@ARGV; $self->{'found'} ||= []; $self->{'temp_file_list'} ||= []; - - + + $self->{'target'} = undef; $self->init_formatter_class_list; @@ -383,7 +457,7 @@ sub init_formatter_class_list { $self->opt_M_with('Pod::Perldoc::ToPod'); # the always-there fallthru $self->opt_o_with('text'); - $self->opt_o_with('man') unless IS_MSWin32 || IS_Dos + $self->opt_o_with('man') unless $self->is_mswin32 || $self->is_dos || !($ENV{TERM} && ( ($ENV{TERM} || '') !~ /dumb|emacs|none|unknown/i )); @@ -413,14 +487,14 @@ sub process { # TODO: make it deal with being invoked as various different things # such as perlfaq". - + return $self->usage_brief unless @{ $self->{'args'} }; $self->pagers_guessing; $self->options_reading; $self->aside(sprintf "$0 => %s v%s\n", ref($self), $self->VERSION); $self->drop_privs_maybe; $self->options_processing; - + # Hm, we have @pages and @found, but we only really act on one # file per call, with the exception of the opt_q hack, and with # -l things @@ -429,7 +503,7 @@ sub process { my @pages; $self->{'pages'} = \@pages; - if( $self->opt_f) { @pages = ("perlfunc") } + if( $self->opt_f) { @pages = qw(perlfunc perlop) } elsif( $self->opt_q) { @pages = ("perlfaq1" .. "perlfaq9") } elsif( $self->opt_v) { @pages = ("perlvar") } else { @pages = @{$self->{'args'}}; @@ -444,10 +518,10 @@ sub process { $self->maybe_diddle_INC(); # for when we're apparently in a module or extension directory - + my @found = $self->grand_search_init(\@pages); - exit (IS_VMS ? 98962 : 1) unless @found; - + exit ($self->is_vms ? 98962 : 1) unless @found; + if ($self->opt_l) { DEBUG and print "We're in -l mode, so byebye after this:\n"; print join("\n", @found), "\n"; @@ -469,8 +543,8 @@ my( %class_seen, %class_loaded ); sub find_good_formatter_class { my $self = $_[0]; my @class_list = @{ $self->{'formatter_classes'} || [] }; - die "WHAT? Nothing in the formatter class list!?" unless @class_list; - + $self->die( "WHAT? Nothing in the formatter class list!?" ) unless @class_list; + my $good_class_found; foreach my $c (@class_list) { DEBUG > 4 and print "Trying to load $c...\n"; @@ -479,21 +553,21 @@ sub find_good_formatter_class { $good_class_found = $c; last; } - + if($class_seen{$c}) { DEBUG > 4 and print "I've tried $c before, and it's no good. Skipping.\n"; next; } - + $class_seen{$c} = 1; - + if( $c->can('parse_from_file') ) { DEBUG > 4 and print "Interesting, the formatter class $c is already loaded!\n"; - + } elsif( - (IS_VMS or IS_MSWin32 or IS_Dos or IS_OS2) + ( $self->is_os2 or $self->is_mswin32 or $self->is_dos or $self->is_os2) # the always case-insensitive filesystems and $class_seen{lc("~$c")}++ ) { @@ -518,7 +592,7 @@ sub find_good_formatter_class { next; } } - + if( $c->can('parse_from_file') ) { DEBUG > 4 and print "Settling on $c\n"; my $v = $c->VERSION; @@ -530,13 +604,13 @@ sub find_good_formatter_class { DEBUG > 4 and print "Class $c isn't a formatter?! Skipping.\n"; } } - - die "Can't find any loadable formatter class in @class_list?!\nAborting" + + $self->die( "Can't find any loadable formatter class in @class_list?!\nAborting" ) unless $good_class_found; - + $self->{'formatter_class'} = $good_class_found; $self->aside("Will format with the class $good_class_found\n"); - + return; } @@ -546,8 +620,8 @@ sub find_good_formatter_class { sub formatter_sanity_check { my $self = shift; my $formatter_class = $self->{'formatter_class'} - || die "NO FORMATTER CLASS YET!?"; - + || $self->die( "NO FORMATTER CLASS YET!?" ); + if(!$self->opt_T # so -T can FORCE sending to STDOUT and $formatter_class->can('is_pageable') and !$formatter_class->is_pageable @@ -558,12 +632,12 @@ sub formatter_sanity_check { && $formatter_class->output_extension ) || ''; $ext = ".$ext" if length $ext; - + my $me = $self->program_name; - die + $self->die( "When using Perldoc to format with $formatter_class, you have to\n" . "specify -T or -dsomefile$ext\n" - . "See '$me perldoc' for more information on those switches.\n" + . "See `$me perldoc' for more information on those switches.\n" ) ; } } @@ -572,18 +646,18 @@ sub formatter_sanity_check { sub render_and_page { my($self, $found_list) = @_; - + $self->maybe_generate_dynamic_pod($found_list); my($out, $formatter) = $self->render_findings($found_list); - + if($self->opt_d) { printf "Perldoc (%s) output saved to %s\n", $self->{'formatter_class'} || ref($self), $out; print "But notice that it's 0 bytes long!\n" unless -s $out; - - + + } elsif( # Allow the formatter to "page" itself, if it wants. $formatter->can('page_for_perldoc') and do { @@ -598,25 +672,25 @@ sub render_and_page { } ) { # Do nothing, since the formatter has "paged" it for itself. - + } else { # Page it normally (internally) - + if( -s $out ) { # Usual case: $self->page($out, $self->{'output_to_stdout'}, $self->pagers); - + } else { # Odd case: $self->aside("Skipping $out (from $$found_list[0] " . "via $$self{'formatter_class'}) as it is 0-length.\n"); - + push @{ $self->{'temp_file_list'} }, $out; $self->unlink_if_temp_file($out); } } - + $self->after_rendering(); # any extra cleanup or whatever - + return; } @@ -624,7 +698,7 @@ sub render_and_page { sub options_reading { my $self = shift; - + if( defined $ENV{"PERLDOC"} and length $ENV{"PERLDOC"} ) { require Text::ParseWords; $self->aside("Noting env PERLDOC setting of $ENV{'PERLDOC'}\n"); @@ -647,7 +721,7 @@ sub options_reading { and print " Args after switch processing: @{$self->{'args'}}\n"; return $self->usage if $self->opt_h; - + return; } @@ -655,7 +729,7 @@ sub options_reading { sub options_processing { my $self = shift; - + if ($self->opt_X) { my $podidx = "$Config{'archlib'}/pod.idx"; $podidx = "" unless -f $podidx && -r _ && -M _ <= 7; @@ -666,8 +740,11 @@ sub options_processing { $self->options_sanity; - $self->opt_n("nroff") unless $self->opt_n; - $self->add_formatter_option( '__nroffer' => $self->opt_n ); + # This used to set a default, but that's now moved into any + # formatter that cares to have a default. + if( $self->opt_n ) { + $self->add_formatter_option( '__nroffer' => $self->opt_n ); + } # Get language from PERLDOC_POD2 environment variable if ( ! $self->opt_L && $ENV{PERLDOC_POD2} ) { @@ -700,19 +777,19 @@ sub options_sanity { #; # #$self->usage("only one of -t, -u, -m or -l") if $opts > 1; - - + + # Any sanity-checking need doing here? - - # But does not make sense to set either -f or -q in $ENV{"PERLDOC"} - if( $self->opt_f or $self->opt_q ) { - $self->usage("Only one of -f -or -q") if $self->opt_f and $self->opt_q; - warn - "Perldoc is only really meant for reading one word at a time.\n", - "So these parameters are being ignored: ", - join(' ', @{$self->{'args'}}), - "\n" - if @{$self->{'args'}} + + # But does not make sense to set either -f or -q in $ENV{"PERLDOC"} + if( $self->opt_f or $self->opt_q ) { + $self->usage("Only one of -f -or -q") if $self->opt_f and $self->opt_q; + $self->warn( + "Perldoc is only really meant for reading one word at a time.\n", + "So these parameters are being ignored: ", + join(' ', @{$self->{'args'}}), + "\n" ) + if @{$self->{'args'}} } return; } @@ -737,7 +814,7 @@ sub grand_search_init { } else { print STDERR "No " . - ($self->opt_m ? "module" : "documentation") . " found for \"$_\".\n"; + ($self->opt_m ? "module" : "documentation") . " found for \"$_\".\n"; } next; } @@ -749,7 +826,7 @@ sub grand_search_init { chomp; push(@found, $_) if m,/$searchfor(?:\.(?:pod|pm))?\z,i; } - close(PODIDX) or die "Can't close $$self{'podidx'}: $!"; + close(PODIDX) or $self->die( "Can't close $$self{'podidx'}: $!" ); next; } @@ -757,7 +834,7 @@ sub grand_search_init { if ($self->opt_F) { next unless -r; - push @found, $_ if $self->opt_m or $self->containspod($_); + push @found, $_ if $self->opt_l or $self->opt_m or $self->containspod($_); next; } @@ -770,7 +847,7 @@ sub grand_search_init { # for executables, like h2xs or perldoc itself. push @searchdirs, ($self->{'bindir'}, @INC); unless ($self->opt_m) { - if (IS_VMS) { + if ($self->is_vms) { my($i,$trn); for ($i = 0; $trn = $ENV{'DCL$PATH;'.$i}; $i++) { push(@searchdirs,$trn); @@ -787,7 +864,7 @@ sub grand_search_init { $self->aside( "Found as @files\n" ); } # add "perl" prefix, so "perldoc foo" may find perlfoo.pod - elsif (BE_LENIENT and !/\W/ and @files = $self->searchfor(0, "perl$_", @searchdirs)) { + elsif (BE_LENIENT and !/\W/ and @files = $self->searchfor(0, "perl$_", @searchdirs)) { $self->aside( "Loosely found as @files\n" ); } else { @@ -804,13 +881,13 @@ sub grand_search_init { print STDERR "However, try\n"; my $me = $self->program_name; for my $dir (@{ $self->{'found'} }) { - opendir(DIR, $dir) or die "opendir $dir: $!"; + opendir(DIR, $dir) or $self->die( "opendir $dir: $!" ); while (my $file = readdir(DIR)) { next if ($file =~ /^\./s); $file =~ s/\.(pm|pod)\z//; # XXX: badfs print STDERR "\t$me $_\::$file\n"; } - closedir(DIR) or die "closedir $dir: $!"; + closedir(DIR) or $self->die( "closedir $dir: $!" ); } } } @@ -825,11 +902,11 @@ sub grand_search_init { sub maybe_generate_dynamic_pod { my($self, $found_things) = @_; my @dynamic_pod; - + $self->search_perlfunc($found_things, \@dynamic_pod) if $self->opt_f; $self->search_perlvar($found_things, \@dynamic_pod) if $self->opt_v; - + $self->search_perlfaqs($found_things, \@dynamic_pod) if $self->opt_q; if( ! $self->opt_f and ! $self->opt_q and ! $self->opt_v ) { @@ -837,22 +914,22 @@ sub maybe_generate_dynamic_pod { } elsif ( @dynamic_pod ) { $self->aside("Hm, I found some Pod from that search!\n"); my ($buffd, $buffer) = $self->new_tempfile('pod', 'dyn'); - + push @{ $self->{'temp_file_list'} }, $buffer; # I.e., it MIGHT be deleted at the end. - - my $in_list = $self->opt_f || $self->opt_v; + + my $in_list = !$self->not_dynamic && $self->opt_f || $self->opt_v; print $buffd "=over 8\n\n" if $in_list; - print $buffd @dynamic_pod or die "Can't print $buffer: $!"; + print $buffd @dynamic_pod or $self->die( "Can't print $buffer: $!" ); print $buffd "=back\n" if $in_list; - close $buffd or die "Can't close $buffer: $!"; - + close $buffd or $self->die( "Can't close $buffer: $!" ); + @$found_things = $buffer; # Yes, so found_things never has more than one thing in # it, by time we leave here - + $self->add_formatter_option('__filter_nroff' => 1); } else { @@ -865,13 +942,21 @@ sub maybe_generate_dynamic_pod { #.......................................................................... +sub not_dynamic { + my ($self,$value) = @_; + $self->{__not_dynamic} = $value if @_ == 2; + return $self->{__not_dynamic}; +} + +#.......................................................................... + sub add_formatter_option { # $self->add_formatter_option('key' => 'value'); my $self = shift; push @{ $self->{'formatter_switches'} }, [ @_ ] if @_; DEBUG > 3 and printf "Formatter switches now: [%s]\n", join ' ', map "[@$_]", @{ $self->{'formatter_switches'} }; - + return; } @@ -884,12 +969,12 @@ sub new_translator { # $tr = $self->new_translator($lang); my $pack = 'POD2::' . uc($lang); eval "require $pack"; if ( !$@ && $pack->can('new') ) { - return $pack->new(); + return $pack->new(); } eval { require POD2::Base }; return if $@; - + return POD2::Base->new({ lang => $lang }); } @@ -906,7 +991,7 @@ sub add_translator { # $self->add_translator($lang); $self->aside( "translator for '$lang' loaded\n" ); } else { # non-installed or bad translator package - warn "Perldoc cannot load translator package for '$lang': ignored\n"; + $self->warn( "Perldoc cannot load translator package for '$lang': ignored\n" ); } } @@ -921,14 +1006,14 @@ sub search_perlvar { my $opt = $self->opt_v; if ( $opt !~ /^ (?: [\@\%\$]\S+ | [A-Z]\w* ) $/x ) { - die "'$opt' does not look like a Perl variable\n"; + $self->die( "'$opt' does not look like a Perl variable\n" ); } DEBUG > 2 and print "Search: @$found_things\n"; - + my $perlvar = shift @$found_things; open(PVAR, "<", $perlvar) # "Funk is its own reward" - or die("Can't open $perlvar: $!"); + or $self->die("Can't open $perlvar: $!"); if ( $opt ne '$0' && $opt =~ /^\$\d+$/ ) { # handle $1, $2, ... $opt = '$<I<digits>>'; @@ -937,7 +1022,7 @@ sub search_perlvar { DEBUG > 2 and print "Going to perlvar-scan for $search_re in $perlvar\n"; - + # Skip introduction local $_; while (<PVAR>) { @@ -960,13 +1045,13 @@ sub search_perlvar { elsif (!/^\s+$/) { # not a blank line if ( $found ) { $inheader = 0; # don't accept more =item (unless inlist) - } + } else { @$pod = (); # reset $inheader = 1; # start over next; } - } + } if (/^=over/) { ++$inlist; @@ -980,15 +1065,68 @@ sub search_perlvar { } @$pod = () unless $found; if (!@$pod) { - die "No documentation for perl variable '$opt' found\n"; + $self->die( "No documentation for perl variable '$opt' found\n" ); } - close PVAR or die "Can't open $perlvar: $!"; + close PVAR or $self->die( "Can't open $perlvar: $!" ); return; } #.......................................................................... +sub search_perlop { + my ($self,$found_things,$pod) = @_; + + $self->not_dynamic( 1 ); + + my $perlop = shift @$found_things; + open( PERLOP, '<', $perlop ) or $self->die( "Can't open $perlop: $!" ); + + my $paragraph = ""; + my $has_text_seen = 0; + my $thing = $self->opt_f; + my $list = 0; + + while( my $line = <PERLOP> ){ + if( $paragraph and $line =~ m!^=(?:head|item)! and $paragraph =~ m!X<+\s*\Q$thing\E\s*>+! ){ + if( $list ){ + $paragraph =~ s!=back.*?\z!!s; + } + + if( $paragraph =~ m!^=item! ){ + $paragraph = "=over 8\n\n" . $paragraph . "=back\n"; + } + + push @$pod, $paragraph; + $paragraph = ""; + $has_text_seen = 0; + $list = 0; + } + + if( $line =~ m!^=over! ){ + $list++; + } + elsif( $line =~ m!^=back! ){ + $list--; + } + + if( $line =~ m!^=(?:head|item)! and $has_text_seen ){ + $paragraph = ""; + } + elsif( $line !~ m!^=(?:head|item)! and $line !~ m!^\s*$! and $line !~ m!^\s*X<! ){ + $has_text_seen = 1; + } + + $paragraph .= $line; + } + + close PERLOP; + + return; +} + +#.......................................................................... + sub search_perlfunc { my($self, $found_things, $pod) = @_; @@ -996,9 +1134,9 @@ sub search_perlfunc { my $perlfunc = shift @$found_things; open(PFUNC, "<", $perlfunc) # "Funk is its own reward" - or die("Can't open $perlfunc: $!"); + or $self->die("Can't open $perlfunc: $!"); - # Functions like -r, -e, etc. are listed under '-X'. + # Functions like -r, -e, etc. are listed under `-X'. my $search_re = ($self->opt_f =~ /^-[rwxoRWXOeszfdlpSbctugkTBMAC]$/) ? '(?:I<)?-X' : quotemeta($self->opt_f) ; @@ -1022,13 +1160,31 @@ sub search_perlfunc { # Look for our function my $found = 0; my $inlist = 0; + + my @perlops = qw(m q qq qr qx qw s tr y); + + my @related; + my $related_re; while (<PFUNC>) { # "The Mothership Connection is here!" + last if( grep{ $self->opt_f eq $_ }@perlops ); if ( m/^=item\s+$search_re\b/ ) { $found = 1; } + elsif (@related > 1 and /^=item/) { + $related_re ||= join "|", @related; + if (m/^=item\s+(?:$related_re)\b/) { + $found = 1; + } + else { + last; + } + } elsif (/^=item/) { last if $found > 1 and not $inlist; } + elsif ($found and /^X<[^>]+>/) { + push @related, m/X<([^>]+)>/g; + } next unless $found; if (/^=over/) { ++$inlist; @@ -1040,13 +1196,18 @@ sub search_perlfunc { push @$pod, $_; ++$found if /^\w/; # found descriptive text } + + if( !@$pod ){ + $self->search_perlop( $found_things, $pod ); + } + if (!@$pod) { - die sprintf - "No documentation for perl function '%s' found\n", - $self->opt_f + $self->die( sprintf + "No documentation for perl function `%s' found\n", + $self->opt_f ) ; } - close PFUNC or die "Can't open $perlfunc: $!"; + close PFUNC or $self->die( "Can't open $perlfunc: $!" ); return; } @@ -1059,9 +1220,9 @@ sub search_perlfaqs { my $found = 0; my %found_in; my $search_key = $self->opt_q; - + my $rx = eval { qr/$search_key/ } - or die <<EOD; + or $self->die( <<EOD ); Invalid regular expression '$search_key' given as -q pattern: $@ Did you mean \\Q$search_key ? @@ -1070,9 +1231,9 @@ EOD local $_; foreach my $file (@$found_things) { - die "invalid file spec: $!" if $file =~ /[<>|]/; + $self->die( "invalid file spec: $!" ) if $file =~ /[<>|]/; open(INFAQ, "<", $file) # XXX 5.6ism - or die "Can't read-open $file: $!\nAborting"; + or $self->die( "Can't read-open $file: $!\nAborting" ); while (<INFAQ>) { if ( m/^=head2\s+.*(?:$search_key)/i ) { $found = 1; @@ -1086,7 +1247,7 @@ EOD } close(INFAQ); } - die("No documentation for perl FAQ keyword '$search_key' found\n") + $self->die("No documentation for perl FAQ keyword `$search_key' found\n") unless @$pod; return; @@ -1101,25 +1262,25 @@ sub render_findings { my($self, $found_things) = @_; my $formatter_class = $self->{'formatter_class'} - || die "No formatter class set!?"; + || $self->die( "No formatter class set!?" ); my $formatter = $formatter_class->can('new') ? $formatter_class->new : $formatter_class ; if(! @$found_things) { - die "Nothing found?!"; + $self->die( "Nothing found?!" ); # should have been caught before here } elsif(@$found_things > 1) { - warn + $self->warn( "Perldoc is only really meant for reading one document at a time.\n", "So these parameters are being ignored: ", join(' ', @$found_things[1 .. $#$found_things] ), - "\n" + "\n" ); } my $file = $found_things->[0]; - + DEBUG > 3 and printf "Formatter switches now: [%s]\n", join ' ', map "[@$_]", @{ $self->{'formatter_switches'} }; @@ -1129,18 +1290,18 @@ sub render_findings { my($switch, $value, $silent_fail) = @$f; if( $formatter->can($switch) ) { eval { $formatter->$switch( defined($value) ? $value : () ) }; - warn "Got an error when setting $formatter_class\->$switch:\n$@\n" + $self->warn( "Got an error when setting $formatter_class\->$switch:\n$@\n" ) if $@; } else { if( $silent_fail or $switch =~ m/^__/s ) { DEBUG > 2 and print "Formatter $formatter_class doesn't support $switch\n"; } else { - warn "$formatter_class doesn't recognize the $switch switch.\n"; + $self->warn( "$formatter_class doesn't recognize the $switch switch.\n" ); } } } } - + $self->{'output_is_binary'} = $formatter->can('write_with_binmode') && $formatter->write_with_binmode; @@ -1165,19 +1326,19 @@ sub render_findings { # The average user just has no reason to be seeing # $^W-suppressible warnings from the formatting! } - + eval { $formatter->parse_from_file( $file, $out_fh ) }; } - - warn "Error while formatting with $formatter_class:\n $@\n" if $@; + + $self->warn( "Error while formatting with $formatter_class:\n $@\n" ) if $@; DEBUG > 2 and print "Back from formatting with $formatter_class\n"; - close $out_fh - or warn "Can't close $out: $!\n(Did $formatter already close it?)"; + close $out_fh + or $self->warn( "Can't close $out: $!\n(Did $formatter already close it?)" ); sleep 0; sleep 0; sleep 0; # Give the system a few timeslices to meditate on the fact # that the output file does in fact exist and is closed. - + $self->unlink_if_temp_file($file); unless( -s $out ) { @@ -1187,7 +1348,7 @@ sub render_findings { # as a 0-length output file? $formatter->if_zero_length( $file, $out, $out_fh ); } else { - warn "Got a 0-length file from $$found_things[0] via $formatter_class!?\n" + $self->warn( "Got a 0-length file from $$found_things[0] via $formatter_class!?\n" ); } } @@ -1206,11 +1367,11 @@ sub unlink_if_temp_file { # my($self, $file) = @_; return unless defined $file and length $file; - + my $temp_file_list = $self->{'temp_file_list'} || return; if(grep $_ eq $file, @$temp_file_list) { $self->aside("Unlinking $file\n"); - unlink($file) or warn "Odd, couldn't unlink $file: $!"; + unlink($file) or $self->warn( "Odd, couldn't unlink $file: $!" ); } else { DEBUG > 1 and print "$file isn't a temp file, so not unlinking.\n"; } @@ -1219,129 +1380,25 @@ sub unlink_if_temp_file { #.......................................................................... -sub MSWin_temp_cleanup { - - # Nothing particularly MSWin-specific in here, but I don't know if any - # other OS needs its temp dir policed like MSWin does! - - my $self = shift; - - my $tempdir = $ENV{'TEMP'}; - return unless defined $tempdir and length $tempdir - and -e $tempdir and -d _ and -w _; - - $self->aside( - "Considering whether any old files of mine in $tempdir need unlinking.\n" - ); - - opendir(TMPDIR, $tempdir) || return; - my @to_unlink; - - my $limit = time() - $Temp_File_Lifetime; - - DEBUG > 5 and printf "Looking for things pre-dating %s (%x)\n", - ($limit) x 2; - - my $filespec; - - while(defined($filespec = readdir(TMPDIR))) { - if( - $filespec =~ m{^perldoc_[a-zA-Z0-9]+_T([a-fA-F0-9]{7,})_[a-fA-F0-9]{3,}}s - ) { - if( hex($1) < $limit ) { - push @to_unlink, "$tempdir/$filespec"; - $self->aside( "Will unlink my old temp file $to_unlink[-1]\n" ); - } else { - DEBUG > 5 and - printf " $tempdir/$filespec is too recent (after %x)\n", $limit; - } - } else { - DEBUG > 5 and - print " $tempdir/$filespec doesn't look like a perldoc temp file.\n"; - } - } - closedir(TMPDIR); - $self->aside(sprintf "Unlinked %s items of mine in %s\n", - scalar(unlink(@to_unlink)), - $tempdir - ); - return; -} - -# . . . . . . . . . . . . . . . . . . . . . . . . . - -sub MSWin_perldoc_tempfile { - my($self, $suffix, $infix) = @_; - - my $tempdir = $ENV{'TEMP'}; - return unless defined $tempdir and length $tempdir - and -e $tempdir and -d _ and -w _; - - my $spec; - - do { - $spec = sprintf "%s\\perldoc_%s_T%x_%x%02x.%s", # used also in MSWin_temp_cleanup - # Yes, we embed the create-time in the filename! - $tempdir, - $infix || 'x', - time(), - $$, - defined( &Win32::GetTickCount ) - ? (Win32::GetTickCount() & 0xff) - : int(rand 256) - # Under MSWin, $$ values get reused quickly! So if we ran - # perldoc foo and then perldoc bar before there was time for - # time() to increment time."_$$" would likely be the same - # for each process! So we tack on the tick count's lower - # bits (or, in a pinch, rand) - , - $suffix || 'txt'; - ; - } while( -e $spec ); - - my $counter = 0; - - while($counter < 50) { - my $fh; - # If we are running before perl5.6.0, we can't autovivify - if ($] < 5.006) { - require Symbol; - $fh = Symbol::gensym(); - } - DEBUG > 3 and print "About to try making temp file $spec\n"; - return($fh, $spec) if open($fh, ">", $spec); # XXX 5.6ism - $self->aside("Can't create temp file $spec: $!\n"); - } - - $self->aside("Giving up on making a temp file!\n"); - die "Can't make a tempfile!?"; -} - -#.......................................................................... - sub after_rendering { my $self = $_[0]; - $self->after_rendering_VMS if IS_VMS; - $self->after_rendering_MSWin32 if IS_MSWin32; - $self->after_rendering_Dos if IS_Dos; - $self->after_rendering_OS2 if IS_OS2; + $self->after_rendering_VMS if $self->is_vms; + $self->after_rendering_MSWin32 if $self->is_mswin32; + $self->after_rendering_Dos if $self->is_dos; + $self->after_rendering_OS2 if $self->is_os2; return; } sub after_rendering_VMS { return } sub after_rendering_Dos { return } sub after_rendering_OS2 { return } - -sub after_rendering_MSWin32 { - shift->MSWin_temp_cleanup() if $Temp_Files_Created; -} +sub after_rendering_MSWin32 { return } #.......................................................................... -# : : : : : : : : : +# : : : : : : : : : #.......................................................................... - sub minus_f_nocase { # i.e., do like -f, but without regard to case my($self, $dir, $file) = @_; @@ -1349,59 +1406,59 @@ sub minus_f_nocase { # i.e., do like -f, but without regard to case return $path if -f $path and -r _; if(!$self->opt_i - or IS_VMS or IS_MSWin32 - or IS_Dos or IS_OS2 + or $self->is_vms or $self->is_mswin32 + or $self->Is_dos or $self->is_os2 ) { # On a case-forgiving file system, or if case is important, - # that is it, all we can do. - warn "Ignored $path: unreadable\n" if -f _; - return ''; + # that is it, all we can do. + $self->warn( "Ignored $path: unreadable\n" ) if -f _; + return ''; } - + local *DIR; my @p = ($dir); my($p,$cip); foreach $p (splitdir $file){ - my $try = catfile @p, $p; + my $try = catfile @p, $p; $self->aside("Scrutinizing $try...\n"); - stat $try; - if (-d _) { - push @p, $p; - if ( $p eq $self->{'target'} ) { - my $tmp_path = catfile @p; - my $path_f = 0; - for (@{ $self->{'found'} }) { - $path_f = 1 if $_ eq $tmp_path; - } - push (@{ $self->{'found'} }, $tmp_path) unless $path_f; - $self->aside( "Found as $tmp_path but directory\n" ); - } - } - elsif (-f _ && -r _) { - return $try; - } - elsif (-f _) { - warn "Ignored $try: unreadable\n"; - } - elsif (-d catdir(@p)) { # at least we see the containing directory! - my $found = 0; - my $lcp = lc $p; - my $p_dirspec = catdir(@p); - opendir DIR, $p_dirspec or die "opendir $p_dirspec: $!"; - while(defined( $cip = readdir(DIR) )) { - if (lc $cip eq $lcp){ - $found++; - last; # XXX stop at the first? what if there's others? - } - } - closedir DIR or die "closedir $p_dirspec: $!"; - return "" unless $found; - - push @p, $cip; - my $p_filespec = catfile(@p); - return $p_filespec if -f $p_filespec and -r _; - warn "Ignored $p_filespec: unreadable\n" if -f _; - } + stat $try; + if (-d _) { + push @p, $p; + if ( $p eq $self->{'target'} ) { + my $tmp_path = catfile @p; + my $path_f = 0; + for (@{ $self->{'found'} }) { + $path_f = 1 if $_ eq $tmp_path; + } + push (@{ $self->{'found'} }, $tmp_path) unless $path_f; + $self->aside( "Found as $tmp_path but directory\n" ); + } + } + elsif (-f _ && -r _ && lc($try) eq lc($path)) { + return $try; + } + elsif (-f _) { + $self->warn( "Ignored $try: unreadable or file/dir mismatch\n" ); + } + elsif (-d catdir(@p)) { # at least we see the containing directory! + my $found = 0; + my $lcp = lc $p; + my $p_dirspec = catdir(@p); + opendir DIR, $p_dirspec or $self->die( "opendir $p_dirspec: $!" ); + while(defined( $cip = readdir(DIR) )) { + if (lc $cip eq $lcp){ + $found++; + last; # XXX stop at the first? what if there's others? + } + } + closedir DIR or $self->die( "closedir $p_dirspec: $!" ); + return "" unless $found; + + push @p, $cip; + my $p_filespec = catfile(@p); + return $p_filespec if -f $p_filespec and -r _; + $self->warn( "Ignored $p_filespec: unreadable\n" ) if -f _; + } } return ""; } @@ -1415,34 +1472,35 @@ sub pagers_guessing { push @pagers, $self->pagers; $self->{'pagers'} = \@pagers; - if (IS_MSWin32) { + if ($self->is_mswin32) { push @pagers, qw( more< less notepad ); unshift @pagers, $ENV{PAGER} if $ENV{PAGER}; } - elsif (IS_VMS) { + elsif ($self->is_vms) { push @pagers, qw( most more less type/page ); } - elsif (IS_Dos) { + elsif ($self->is_dos) { push @pagers, qw( less.exe more.com< ); unshift @pagers, $ENV{PAGER} if $ENV{PAGER}; } else { - if (IS_OS2) { + if ($self->is_os2) { unshift @pagers, 'less', 'cmd /c more <'; } push @pagers, qw( more less pg view cat ); - unshift @pagers, $ENV{PAGER} if $ENV{PAGER}; + unshift @pagers, "$ENV{PAGER}<" if $ENV{PAGER}; } - if (IS_Cygwin) { + if ($self->is_cygwin) { if (($pagers[0] eq 'less') || ($pagers[0] eq '/usr/bin/less')) { unshift @pagers, '/usr/bin/less -isrR'; - } + unshift @pagers, $ENV{PAGER} if $ENV{PAGER}; + } } unshift @pagers, $ENV{PERLDOC_PAGER} if $ENV{PERLDOC_PAGER}; - - return; + + return; } #.......................................................................... @@ -1462,62 +1520,23 @@ sub page_module_file { # occasionally hazy distinction between OS-local extension # associations, and browser-specific MIME mappings. - if ($self->{'output_to_stdout'}) { - $self->aside("Sending unpaged output to STDOUT.\n"); - local $_; - my $any_error = 0; - foreach my $output (@found) { - unless( open(TMP, "<", $output) ) { # XXX 5.6ism - warn("Can't open $output: $!"); - $any_error = 1; - next; - } - while (<TMP>) { - print or die "Can't print to stdout: $!"; - } - close TMP or die "Can't close while $output: $!"; - $self->unlink_if_temp_file($output); - } - return $any_error; # successful + if(@found > 1) { + $self->warn( + "Perldoc is only really meant for reading one document at a time.\n" . + "So these files are being ignored: " . + join(' ', @found[1 .. $#found] ) . + "\n" ) } - foreach my $pager ( $self->pagers ) { - $self->aside("About to try calling $pager @found\n"); - if (system($pager, @found) == 0) { - $self->aside("Yay, it worked.\n"); - return 0; - } - $self->aside("That didn't work.\n"); - - # Odd -- when it fails, under Win32, this seems to neither - # return with a fail nor return with a success!! - # That's discouraging! - } + return $self->page($found[0], $self->{'output_to_stdout'}, $self->pagers); - $self->aside( - sprintf "Can't manage to find a way to page [%s] via pagers [%s]\n", - join(' ', @found), - join(' ', $self->pagers), - ); - - if (IS_VMS) { - DEBUG > 1 and print "Bailing out in a VMSish way.\n"; - eval q{ - use vmsish qw(status exit); - exit $?; - 1; - } or die; - } - - return 1; - # i.e., an UNSUCCESSFUL return value! } #.......................................................................... sub check_file { my($self, $dir, $file) = @_; - + unless( ref $self ) { # Should never get called: $Carp::Verbose = 1; @@ -1528,29 +1547,41 @@ sub check_file { "Aborting" ); } - + if(length $dir and not -d $dir) { DEBUG > 3 and print " No dir $dir -- skipping.\n"; return ""; } - - if ($self->opt_m) { - return $self->minus_f_nocase($dir,$file); - } - - else { - my $path = $self->minus_f_nocase($dir,$file); - if( length $path and $self->containspod($path) ) { - DEBUG > 3 and print - " The file $path indeed looks promising!\n"; - return $path; - } + + my $path = $self->minus_f_nocase($dir,$file); + if( length $path and ($self->opt_m ? $self->isprintable($path) + : $self->containspod($path)) ) { + DEBUG > 3 and print + " The file $path indeed looks promising!\n"; + return $path; } DEBUG > 3 and print " No good: $file in $dir\n"; - + return ""; } +sub isprintable { + my($self, $file, $readit) = @_; + my $size= 1024; + my $maxunprintfrac= 0.2; # tolerate some unprintables for UTF-8 comments etc. + + return 1 if !$readit && $file =~ /\.(?:pl|pm|pod|cmd|com|bat)\z/i; + + my $data; + local($_); + open(TEST,"<", $file) or $self->die( "Can't open $file: $!" ); + read TEST, $data, $size; + close TEST; + $size= length($data); + $data =~ tr/\x09-\x0D\x20-\x7E//d; + return length($data) <= $size*$maxunprintfrac; +} + #.......................................................................... sub containspod { @@ -1571,21 +1602,21 @@ sub containspod { # # $ perldoc perl.pod - if ( IS_Cygwin and -x $file and -f "$file.exe" ) + if ( $self->is_cygwin and -x $file and -f "$file.exe" ) { - warn "Cygwin $file.exe search skipped\n" if DEBUG or $self->opt_D; + $self->warn( "Cygwin $file.exe search skipped\n" ) if DEBUG or $self->opt_D; return 0; } local($_); - open(TEST,"<", $file) or die "Can't open $file: $!"; # XXX 5.6ism + open(TEST,"<", $file) or $self->die( "Can't open $file: $!" ); # XXX 5.6ism while (<TEST>) { - if (/^=head/) { - close(TEST) or die "Can't close $file: $!"; - return 1; - } + if (/^=head/) { + close(TEST) or $self->die( "Can't close $file: $!" ); + return 1; + } } - close(TEST) or die "Can't close $file: $!"; + close(TEST) or $self->die( "Can't close $file: $!" ); return 0; } @@ -1593,21 +1624,21 @@ sub containspod { sub maybe_diddle_INC { my $self = shift; - + # Does this look like a module or extension directory? - + if (-f "Makefile.PL" || -f "Build.PL") { # Add "." and "lib" to @INC (if they exist) - eval q{ use lib qw(. lib); 1; } or die; + eval q{ use lib qw(. lib); 1; } or $self->die; # don't add if superuser if ($< && $> && -d "blib") { # don't be looking too hard now! eval q{ use blib; 1 }; - warn $@ if $@ && $self->opt_D; + $self->warn( $@ ) if $@ && $self->opt_D; } } - + return; } @@ -1617,21 +1648,21 @@ sub new_output_file { my $self = shift; my $outspec = $self->opt_d; # Yes, -d overrides all else! # So don't call this twice per format-job! - + return $self->new_tempfile(@_) unless defined $outspec and length $outspec; # Otherwise open a write-handle on opt_d!f my $fh; # If we are running before perl5.6.0, we can't autovivify - if ($] < 5.006) { + if ($^V < 5.006) { require Symbol; $fh = Symbol::gensym(); } DEBUG > 3 and print "About to try writing to specified output file $outspec\n"; - die "Can't write-open $outspec: $!" + $self->die( "Can't write-open $outspec: $!" ) unless open($fh, ">", $outspec); # XXX 5.6ism - + DEBUG > 3 and print "Successfully opened $outspec\n"; binmode($fh) if $self->{'output_is_binary'}; return($fh, $outspec); @@ -1652,7 +1683,7 @@ sub useful_filename_bit { my $self = shift; my $pages = $self->{'pages'} || return undef; return undef unless @$pages; - + my $chunk = $pages->[0]; return undef unless defined $chunk; $chunk =~ s/:://g; @@ -1674,12 +1705,6 @@ sub new_tempfile { # $self->new_tempfile( [$suffix, [$infix] ] ) ++$Temp_Files_Created; - if( IS_MSWin32 ) { - my @out = $self->MSWin_perldoc_tempfile(@_); - return @out if @out; - # otherwise fall thru to the normal stuff below... - } - require File::Temp; return File::Temp::tempfile(UNLINK => 1); } @@ -1690,32 +1715,32 @@ sub page { # apply a pager to the output file my ($self, $output, $output_to_stdout, @pagers) = @_; if ($output_to_stdout) { $self->aside("Sending unpaged output to STDOUT.\n"); - open(TMP, "<", $output) or die "Can't open $output: $!"; # XXX 5.6ism - local $_; - while (<TMP>) { - print or die "Can't print to stdout: $!"; - } - close TMP or die "Can't close while $output: $!"; - $self->unlink_if_temp_file($output); + open(TMP, "<", $output) or $self->die( "Can't open $output: $!" ); # XXX 5.6ism + local $_; + while (<TMP>) { + print or $self->die( "Can't print to stdout: $!" ); + } + close TMP or $self->die( "Can't close while $output: $!" ); + $self->unlink_if_temp_file($output); } else { # On VMS, quoting prevents logical expansion, and temp files with no # extension get the wrong default extension (such as .LIS for TYPE) - $output = VMS::Filespec::rmsexpand($output, '.') if IS_VMS; + $output = VMS::Filespec::rmsexpand($output, '.') if $self->is_vms; - $output =~ s{/}{\\}g if IS_MSWin32 || IS_Dos; - # Altho "/" under MSWin is in theory good as a pathsep, - # many many corners of the OS don't like it. So we - # have to force it to be "\" to make everyone happy. + $output =~ s{/}{\\}g if $self->is_mswin32 || $self->is_dos; + # Altho "/" under MSWin is in theory good as a pathsep, + # many many corners of the OS don't like it. So we + # have to force it to be "\" to make everyone happy. foreach my $pager (@pagers) { $self->aside("About to try calling $pager $output\n"); - if (IS_VMS) { + if ($self->is_vms) { last if system("$pager $output") == 0; } else { - last if system("$pager \"$output\"") == 0; + last if system("$pager \"$output\"") == 0; } - } + } } return; } @@ -1725,7 +1750,7 @@ sub page { # apply a pager to the output file sub searchfor { my($self, $recurse,$s,@dirs) = @_; $s =~ s!::!/!g; - $s = VMS::Filespec::unixify($s) if IS_VMS; + $s = VMS::Filespec::unixify($s) if $self->is_vms; return $s if -f $s && $self->containspod($s); $self->aside( "Looking for $s in @dirs\n" ); my $ret; @@ -1733,41 +1758,41 @@ sub searchfor { my $dir; $self->{'target'} = (splitdir $s)[-1]; # XXX: why not use File::Basename? for ($i=0; $i<@dirs; $i++) { - $dir = $dirs[$i]; - next unless -d $dir; - ($dir = VMS::Filespec::unixpath($dir)) =~ s!/\z!! if IS_VMS; - if ( (! $self->opt_m && ( $ret = $self->check_file($dir,"$s.pod"))) - or ( $ret = $self->check_file($dir,"$s.pm")) - or ( $ret = $self->check_file($dir,$s)) - or ( IS_VMS and - $ret = $self->check_file($dir,"$s.com")) - or ( IS_OS2 and - $ret = $self->check_file($dir,"$s.cmd")) - or ( (IS_MSWin32 or IS_Dos or IS_OS2) and - $ret = $self->check_file($dir,"$s.bat")) - or ( $ret = $self->check_file("$dir/pod","$s.pod")) - or ( $ret = $self->check_file("$dir/pod",$s)) - or ( $ret = $self->check_file("$dir/pods","$s.pod")) - or ( $ret = $self->check_file("$dir/pods",$s)) - ) { - DEBUG > 1 and print " Found $ret\n"; - return $ret; - } - - if ($recurse) { - opendir(D,$dir) or die "Can't opendir $dir: $!"; - my @newdirs = map catfile($dir, $_), grep { - not /^\.\.?\z/s and - not /^auto\z/s and # save time! don't search auto dirs - -d catfile($dir, $_) - } readdir D; - closedir(D) or die "Can't closedir $dir: $!"; - next unless @newdirs; - # what a wicked map! - @newdirs = map((s/\.dir\z//,$_)[1],@newdirs) if IS_VMS; - $self->aside( "Also looking in @newdirs\n" ); - push(@dirs,@newdirs); - } + $dir = $dirs[$i]; + next unless -d $dir; + ($dir = VMS::Filespec::unixpath($dir)) =~ s!/\z!! if $self->is_vms; + if ( (! $self->opt_m && ( $ret = $self->check_file($dir,"$s.pod"))) + or ( $ret = $self->check_file($dir,"$s.pm")) + or ( $ret = $self->check_file($dir,$s)) + or ( $self->is_vms and + $ret = $self->check_file($dir,"$s.com")) + or ( $self->is_os2 and + $ret = $self->check_file($dir,"$s.cmd")) + or ( ($self->is_mswin32 or $self->is_dos or $self->is_os2) and + $ret = $self->check_file($dir,"$s.bat")) + or ( $ret = $self->check_file("$dir/pod","$s.pod")) + or ( $ret = $self->check_file("$dir/pod",$s)) + or ( $ret = $self->check_file("$dir/pods","$s.pod")) + or ( $ret = $self->check_file("$dir/pods",$s)) + ) { + DEBUG > 1 and print " Found $ret\n"; + return $ret; + } + + if ($recurse) { + opendir(D,$dir) or $self->die( "Can't opendir $dir: $!" ); + my @newdirs = map catfile($dir, $_), grep { + not /^\.\.?\z/s and + not /^auto\z/s and # save time! don't search auto dirs + -d catfile($dir, $_) + } readdir D; + closedir(D) or $self->die( "Can't closedir $dir: $!" ); + next unless @newdirs; + # what a wicked map! + @newdirs = map((s/\.dir\z//,$_)[1],@newdirs) if $self->is_vms; + $self->aside( "Also looking in @newdirs\n" ); + push(@dirs,@newdirs); + } } return (); } @@ -1780,10 +1805,10 @@ sub searchfor { return if $already_asserted; - eval q~ END { close(STDOUT) || die "Can't close STDOUT: $!" } ~; + eval q~ END { close(STDOUT) || CORE::die "Can't close STDOUT: $!" } ~; # What for? to let the pager know that nothing more will come? - - die $@ if $@; + + $self->die( $@ ) if $@; $already_asserted = 1; return; } @@ -1793,21 +1818,22 @@ sub searchfor { sub tweak_found_pathnames { my($self, $found) = @_; - if (IS_MSWin32) { + if ($self->is_mswin32) { foreach (@$found) { s,/,\\,g } } + foreach (@$found) { s,',\\',g } # RT 37347 return; } #.......................................................................... -# : : : : : : : : : +# : : : : : : : : : #.......................................................................... sub am_taint_checking { my $self = shift; - die "NO ENVIRONMENT?!?!" unless keys %ENV; # reset iterator along the way + $self->die( "NO ENVIRONMENT?!?!" ) unless keys %ENV; # reset iterator along the way my($k,$v) = each %ENV; - return is_tainted($v); + return is_tainted($v); } #.......................................................................... @@ -1824,10 +1850,10 @@ sub is_tainted { # just a function sub drop_privs_maybe { my $self = shift; - + # Attempt to drop privs if we should be tainting and aren't - if (!(IS_VMS || IS_MSWin32 || IS_Dos - || IS_OS2 + if (!( $self->is_vms || $self->is_mswin32 || $self->is_dos + || $self->is_os2 ) && ($> == 0 || $< == 0) && !$self->am_taint_checking() @@ -1908,94 +1934,11 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut - -# -# -# Perldoc -- look up a piece of documentation in .pod format that -# is embedded in the perl installation tree. -# -#~~~~~~ -# -# See ChangeLog in CPAN dist for Pod::Perldoc for later notes. -# -# Version 3.01: Sun Nov 10 21:38:09 MST 2002 -# Sean M. Burke <sburke@cpan.org> -# Massive refactoring and code-tidying. -# Now it's a module(-family)! -# Formatter-specific stuff pulled out into Pod::Perldoc::To(Whatever).pm -# Added -T, -d, -o, -M, -w. -# Added some improved MSWin funk. -# -#~~~~~~ -# -# Version 2.05: Sat Oct 12 16:09:00 CEST 2002 -# Hugo van der Sanden <hv@crypt.org> -# Made -U the default, based on patch from Simon Cozens -# Version 2.04: Sun Aug 18 13:27:12 BST 2002 -# Randy W. Sims <RandyS@ThePierianSpring.org> -# allow -n to enable nroff under Win32 -# Version 2.03: Sun Apr 23 16:56:34 BST 2000 -# Hugo van der Sanden <hv@crypt.org> -# don't die when 'use blib' fails -# Version 2.02: Mon Mar 13 18:03:04 MST 2000 -# Tom Christiansen <tchrist@perl.com> -# Added -U insecurity option -# Version 2.01: Sat Mar 11 15:22:33 MST 2000 -# Tom Christiansen <tchrist@perl.com>, querulously. -# Security and correctness patches. -# What a twisted bit of distasteful spaghetti code. -# Version 2.0: ???? -# -#~~~~~~ -# -# Version 1.15: Tue Aug 24 01:50:20 EST 1999 -# Charles Wilson <cwilson@ece.gatech.edu> -# changed /pod/ directory to /pods/ for cygwin -# to support cygwin/win32 -# Version 1.14: Wed Jul 15 01:50:20 EST 1998 -# Robin Barker <rmb1@cise.npl.co.uk> -# -strict, -w cleanups -# Version 1.13: Fri Feb 27 16:20:50 EST 1997 -# Gurusamy Sarathy <gsar@activestate.com> -# -doc tweaks for -F and -X options -# Version 1.12: Sat Apr 12 22:41:09 EST 1997 -# Gurusamy Sarathy <gsar@activestate.com> -# -various fixes for win32 -# Version 1.11: Tue Dec 26 09:54:33 EST 1995 -# Kenneth Albanowski <kjahds@kjahds.com> -# -added Charles Bailey's further VMS patches, and -u switch -# -added -t switch, with pod2text support -# -# Version 1.10: Thu Nov 9 07:23:47 EST 1995 -# Kenneth Albanowski <kjahds@kjahds.com> -# -added VMS support -# -added better error recognition (on no found pages, just exit. On -# missing nroff/pod2man, just display raw pod.) -# -added recursive/case-insensitive matching (thanks, Andreas). This -# slows things down a bit, unfortunately. Give a precise name, and -# it'll run faster. -# -# Version 1.01: Tue May 30 14:47:34 EDT 1995 -# Andy Dougherty <doughera@lafcol.lafayette.edu> -# -added pod documentation. -# -added PATH searching. -# -added searching pod/ subdirectory (mainly to pick up perlfunc.pod -# and friends. -# -#~~~~~~~ -# -# TODO: -# -# Cache the directories read during sloppy match -# (To disk, or just in-memory?) -# -# Backport this to perl 5.005? -# -# Implement at least part of the "perlman" interface described -# in Programming Perl 3e? diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/BaseTo.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/BaseTo.pm index 29a3b7d108..ef0f7df2d8 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/BaseTo.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/BaseTo.pm @@ -1,9 +1,14 @@ - -require 5; package Pod::Perldoc::BaseTo; use strict; use warnings; +use vars qw($VERSION); +$VERSION = '3.15_15'; + +use Carp qw(croak carp); +use Config qw(%Config); +use File::Spec::Functions qw(catfile); + sub is_pageable { '' } sub write_with_binmode { 1 } @@ -14,6 +19,22 @@ sub output_extension { 'txt' } # override in subclass! #sub new { return bless {}, ref($_[0]) || $_[0] } +# this is also in Perldoc.pm, but why look there when you're a +# subclass of this? +sub TRUE () {1} +sub FALSE () {return} + +BEGIN { + *is_vms = $^O eq 'VMS' ? \&TRUE : \&FALSE unless defined &is_vms; + *is_mswin32 = $^O eq 'MSWin32' ? \&TRUE : \&FALSE unless defined &is_mswin32; + *is_dos = $^O eq 'dos' ? \&TRUE : \&FALSE unless defined &is_dos; + *is_os2 = $^O eq 'os2' ? \&TRUE : \&FALSE unless defined &is_os2; + *is_cygwin = $^O eq 'cygwin' ? \&TRUE : \&FALSE unless defined &is_cygwin; + *is_linux = $^O eq 'linux' ? \&TRUE : \&FALSE unless defined &is_linux; + *is_hpux = $^O =~ m/hpux/ ? \&TRUE : \&FALSE unless defined &is_hpux; + *is_openbsd = $^O =~ m/openbsd/ ? \&TRUE : \&FALSE unless defined &is_openbsd; +} + sub _perldoc_elem { my($self, $name) = splice @_,0,2; if(@_) { @@ -23,6 +44,54 @@ sub _perldoc_elem { } } +sub debugging { + my( $self, @messages ) = @_; + + ( defined(&Pod::Perldoc::DEBUG) and &Pod::Perldoc::DEBUG() ) + } + +sub debug { + my( $self, @messages ) = @_; + return unless $self->debugging; + print STDERR map { "DEBUG $_" } @messages; + } + +sub warn { + my( $self, @messages ) = @_; + carp join "\n", @messages, ''; + } + +sub die { + my( $self, @messages ) = @_; + croak join "\n", @messages, ''; + } + +sub _get_path_components { + my( $self ) = @_; + + my @paths = split /\Q$Config{path_sep}/, $ENV{PATH}; + + return @paths; + } + +sub _find_executable_in_path { + my( $self, $program ) = @_; + + my @found = (); + foreach my $dir ( $self->_get_path_components ) { + my $binary = catfile( $dir, $program ); + $self->debug( "Looking for $binary\n" ); + next unless -e $binary; + unless( -x $binary ) { + $self->warn( "Found $binary but it's not executable. Skipping.\n" ); + next; + } + $self->debug( "Found $binary\n" ); + push @found, $binary; + } + + return @found; + } 1; @@ -73,9 +142,11 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/GetOptsOO.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/GetOptsOO.pm index fa83fb74cc..0652bb3584 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/GetOptsOO.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/GetOptsOO.pm @@ -1,23 +1,8 @@ - -require 5; package Pod::Perldoc::GetOptsOO; use strict; -# Rather like Getopt::Std's getopts -# Call Pod::Perldoc::GetOptsOO::getopts($object, \@ARGV, $truth) -# Given -n, if there's a opt_n_with, it'll call $object->opt_n_with( ARGUMENT ) -# (e.g., "-n foo" => $object->opt_n_with('foo'). Ditto "-nfoo") -# Otherwise (given -n) if there's an opt_n, we'll call it $object->opt_n($truth) -# (Truth defaults to 1) -# Otherwise we try calling $object->handle_unknown_option('n') -# (and we increment the error count by the return value of it) -# If there's no handle_unknown_option, then we just warn, and then increment -# the error counter -# -# The return value of Pod::Perldoc::GetOptsOO::getopts is true if no errors, -# otherwise it's false. -# -## sburke@cpan.org 2002-10-31 +use vars qw($VERSION); +$VERSION = '3.15_15'; BEGIN { # Make a DEBUG constant ASAP *DEBUG = defined( &Pod::Perldoc::DEBUG ) @@ -28,7 +13,7 @@ BEGIN { # Make a DEBUG constant ASAP sub getopts { my($target, $args, $truth) = @_; - + $args ||= \@ARGV; $target->aside( @@ -54,7 +39,7 @@ sub getopts { if( $target->can($method) ) { # it's argumental if($rest eq '') { # like -f bar shift @$args; - warn "Option $first needs a following argument!\n" unless @$args; + $target->warn( "Option $first needs a following argument!\n" ) unless @$args; $rest = shift @$args; } else { # like -fbar (== -f bar) shift @$args; @@ -75,14 +60,14 @@ sub getopts { } elsif( $target->can('handle_unknown_option') ) { DEBUG > 3 and print " calling handle_unknown_option('$first')\n"; - + $error_count += ( $target->handle_unknown_option( $first ) || 0 ); } else { ++$error_count; - warn "Unknown option: $first\n"; + $target->warn( "Unknown option: $first\n" ); } if($rest eq '') { # like -f @@ -93,7 +78,7 @@ sub getopts { } } } - + $target->aside( "Ending switch processing. Args are [@$args] with $error_count errors.\n" @@ -123,9 +108,32 @@ Pod::Perldoc::GetOptsOO - Customized option parser for Pod::Perldoc Implements a customized option parser used for L<Pod::Perldoc>. +Rather like Getopt::Std's getopts: + +=over + +=item Call Pod::Perldoc::GetOptsOO::getopts($object, \@ARGV, $truth) + +=item Given -n, if there's a opt_n_with, it'll call $object->opt_n_with( ARGUMENT ) + (e.g., "-n foo" => $object->opt_n_with('foo'). Ditto "-nfoo") + +=item Otherwise (given -n) if there's an opt_n, we'll call it $object->opt_n($truth) + (Truth defaults to 1) + +=item Otherwise we try calling $object->handle_unknown_option('n') + (and we increment the error count by the return value of it) + +=item If there's no handle_unknown_option, then we just warn, and then increment + the error counter + +=back + +The return value of Pod::Perldoc::GetOptsOO::getopts is true if no errors, +otherwise it's false. + =head1 SEE ALSO - Pod::Perldoc +L<Pod::Perldoc> =head1 COPYRIGHT AND DISCLAIMERS @@ -140,9 +148,11 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToANSI.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToANSI.pm new file mode 100644 index 0000000000..8c5b34cd62 --- /dev/null +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToANSI.pm @@ -0,0 +1,96 @@ +package Pod::Perldoc::ToANSI; +use strict; +use warnings; +use parent qw(Pod::Perldoc::BaseTo); + +use vars qw($VERSION); +$VERSION = '3.15_15'; + +sub is_pageable { 1 } +sub write_with_binmode { 0 } +sub output_extension { 'txt' } + +use Pod::Text::Color (); + +sub alt { shift->_perldoc_elem('alt' , @_) } +sub indent { shift->_perldoc_elem('indent' , @_) } +sub loose { shift->_perldoc_elem('loose' , @_) } +sub quotes { shift->_perldoc_elem('quotes' , @_) } +sub sentence { shift->_perldoc_elem('sentence', @_) } +sub width { shift->_perldoc_elem('width' , @_) } + +sub new { return bless {}, ref($_[0]) || $_[0] } + +sub parse_from_file { + my $self = shift; + + my @options = + map {; $_, $self->{$_} } + grep !m/^_/s, + keys %$self + ; + + defined(&Pod::Perldoc::DEBUG) + and Pod::Perldoc::DEBUG() + and print "About to call new Pod::Text::Color ", + $Pod::Text::VERSION ? "(v$Pod::Text::VERSION) " : '', + "with options: ", + @options ? "[@options]" : "(nil)", "\n"; + ; + + Pod::Text::Color->new(@options)->parse_from_file(@_); +} + +1; + +=head1 NAME + +Pod::Perldoc::ToANSI - render Pod with ANSI color escapes + +=head1 SYNOPSIS + + perldoc -o ansi Some::Modulename + +=head1 DESCRIPTION + +This is a "plug-in" class that allows Perldoc to use +Pod::Text as a formatter class. + +It supports the following options, which are explained in +L<Pod::Text>: alt, indent, loose, quotes, sentence, width + +For example: + + perldoc -o term -w indent:5 Some::Modulename + +=head1 CAVEAT + +This module may change to use a different text formatter class in the +future, and this may change what options are supported. + +=head1 SEE ALSO + +L<Pod::Text>, L<Pod::Text::Color>, L<Pod::Perldoc> + +=head1 COPYRIGHT AND DISCLAIMERS + +Copyright (c) 2011 Mark Allen. All rights reserved. + +This library is free software; you can redistribute it and/or modify it +under the same terms as Perl itself. + +This program is distributed in the hope that it will be useful, but +without any warranty; without even the implied warranty of +merchantability or fitness for a particular purpose. + +=head1 AUTHOR + +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> + +Past contributions from: +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> + + +=cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToChecker.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToChecker.pm index 10870109e6..c1b87de4e0 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToChecker.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToChecker.pm @@ -1,10 +1,11 @@ - -require 5; package Pod::Perldoc::ToChecker; use strict; use warnings; use vars qw(@ISA); +use vars qw($VERSION); +$VERSION = '3.15_15'; + # Pick our superclass... # eval 'require Pod::Simple::Checker'; @@ -66,10 +67,12 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToMan.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToMan.pm index f456a2475a..1d636247bb 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToMan.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToMan.pm @@ -1,15 +1,22 @@ - -require 5; +require 5.006; package Pod::Perldoc::ToMan; use strict; use warnings; +use parent qw(Pod::Perldoc::BaseTo); + +use vars qw($VERSION); +$VERSION = '3.15_15'; +use File::Spec::Functions qw(catfile); +use Pod::Man 2.18; # This class is unlike ToText.pm et al, because we're NOT paging thru # the output in our particular format -- we make the output and # then we run nroff (or whatever) on it, and then page thru the # (plaintext) output of THAT! -use base qw(Pod::Perldoc::BaseTo); +sub SUCCESS () { 1 } +sub FAILED () { 0 } + sub is_pageable { 1 } sub write_with_binmode { 0 } sub output_extension { 'txt' } @@ -31,108 +38,461 @@ sub quotes { shift->_perldoc_elem('quotes' , @_) } sub release { shift->_perldoc_elem('release' , @_) } sub section { shift->_perldoc_elem('section' , @_) } -sub new { return bless {}, ref($_[0]) || $_[0] } +sub new { + my( $either ) = shift; + my $self = bless {}, ref($either) || $either; + $self->init( @_ ); + return $self; + } -use File::Spec::Functions qw(catfile); +sub init { + my( $self, @args ) = @_; + + unless( $self->__nroffer ) { + my $roffer = $self->_find_roffer( $self->_roffer_candidates ); + $self->debug( "Using $roffer\n" ); + $self->__nroffer( $roffer ); + } + else { + $self->debug( "__nroffer is " . $self->__nroffer() . "\n" ); + } + + $self->_check_nroffer; + } + +sub _roffer_candidates { + my( $self ) = @_; + + if( $self->is_openbsd ) { qw( mandoc groff nroff ) } + else { qw( groff nroff mandoc ) } + } + +sub _find_roffer { + my( $self, @candidates ) = @_; + + my @found = (); + foreach my $candidate ( @candidates ) { + push @found, $self->_find_executable_in_path( $candidate ); + } + + return wantarray ? @found : $found[0]; + } + +sub _check_nroffer { + return 1; + # where is it in the PATH? + + # is it executable? + + # what is its real name? + + # what is its version? + + # does it support the flags we need? + + # is it good enough for us? + } + +sub _get_stty { `stty -a` } + +sub _get_columns_from_stty { + my $output = $_[0]->_get_stty; + + if( $output =~ /\bcolumns\s+(\d+)/ ) { return $1 } + elsif( $output =~ /;\s*(\d+)\s+columns;/ ) { return $1 } + else { return 0 } + } + +sub _get_columns_from_manwidth { + my( $self ) = @_; + + return 0 unless defined $ENV{MANWIDTH}; + + unless( $ENV{MANWIDTH} =~ m/\A\d+\z/ ) { + $self->warn( "Ignoring non-numeric MANWIDTH ($ENV{MANWIDTH})\n" ); + return 0; + } + + if( $ENV{MANWIDTH} == 0 ) { + $self->warn( "Ignoring MANWIDTH of 0. Really? Why even run the program? :)\n" ); + return 0; + } + + if( $ENV{MANWIDTH} =~ m/\A(\d+)\z/ ) { return $1 } + + return 0; + } + +sub _get_default_width { + 73 + } + +sub _get_columns { + $_[0]->_get_columns_from_manwidth || + $_[0]->_get_columns_from_stty || + $_[0]->_get_default_width; + } + +sub _get_podman_switches { + my( $self ) = @_; + + my @switches = grep !m/^_/s, keys %$self; + + push @switches, 'utf8' => 1; + $self->debug( "Pod::Man switches are [@switches]\n" ); + + return @switches; + } + +sub _parse_with_pod_man { + my( $self, $file ) = @_; + + #->output_fh and ->output_string from Pod::Simple aren't + # working, apparently, so there's this ugly hack: + local *STDOUT; + open STDOUT, '>', $self->{_text_ref}; + my $parser = Pod::Man->new( $self->_get_podman_switches ); + $self->debug( "Parsing $file\n" ); + $parser->parse_from_file( $file ); + $self->debug( "Done parsing $file\n" ); + close STDOUT; + + $self->die( "No output from Pod::Man!\n" ) + unless length $self->{_text_ref}; + + $self->_save_pod_man_output if $self->debugging; + + return SUCCESS; + } + +sub _save_pod_man_output { + my( $self, $fh ) = @_; + + $fh = do { + my $file = "podman.out.$$.txt"; + $self->debug( "Writing $file with Pod::Man output\n" ); + open my $fh2, '>', $file; + $fh2; + } unless $fh; + + print { $fh } ${ $self->{_text_ref} }; + } + +sub _have_groff_with_utf8 { + my( $self ) = @_; + + return 0 unless $self->_is_groff; + my $roffer = $self->__nroffer; + + my $minimum_groff_version = '1.20.1'; + + my $version_string = `$roffer -v`; + my( $version ) = $version_string =~ /\(?groff\)? version (\d+\.\d+(?:\.\d+)?)/; + $self->debug( "Found groff $version\n" ); + + # is a string comparison good enough? + if( $version lt $minimum_groff_version ) { + $self->warn( + "You have an old groff." . + " Update to version $minimum_groff_version for good Unicode support.\n" . + "If you don't upgrade, wide characters may come out oddly.\n" + ); + } + + $version gt $minimum_groff_version; + } + +sub _have_mandoc_with_utf8 { + my( $self ) = @_; + + return 0 unless $self->_is_mandoc; + my $roffer = $self->__nroffer; + + my $minimum_mandoc_version = '1.11'; + + my $version_string = `$roffer -V`; + my( $version ) = $version_string =~ /mandoc ((\d+)\.(\d+))/; + $self->debug( "Found mandoc $version\n" ); + + # is a string comparison good enough? + if( $version lt $minimum_mandoc_version ) { + $self->warn( + "You have an older mandoc." . + " Update to version $minimum_mandoc_version for better Unicode support.\n" . + "If you don't upgrade, wide characters may come out oddly.\n" . + "Your results still might be odd. If you have groff, that's even better.\n" + ); + } + + $version gt $minimum_mandoc_version; + } + +sub _collect_nroff_switches { + my( $self ) = shift; + + my @render_switches = $self->_is_mandoc ? qw(-mandoc) : qw(-man); + + push @render_switches, $self->_get_device_switches; + + # Thanks to Brendan O'Dea for contributing the following block + if( $self->_is_roff and $self->is_linux and -t STDOUT and my ($cols) = $self->_get_columns ) { + my $c = $cols * 39 / 40; + $cols = $c > $cols - 2 ? $c : $cols -2; + push @render_switches, '-rLL=' . (int $c) . 'n' if $cols > 80; + } + + # I hear persistent reports that adding a -c switch to $render + # solves many people's problems. But I also hear that some mans + # don't have a -c switch, so that unconditionally adding it here + # would presumably be a Bad Thing -- sburke@cpan.org + push @render_switches, '-c' if( $self->_is_roff and $self->is_cygwin ); + + return @render_switches; + } + +sub _get_device_switches { + my( $self ) = @_; + + if( $self->_is_nroff ) { qw() } + elsif( $self->_have_groff_with_utf8 ) { qw(-Kutf8 -Tutf8) } + elsif( $self->_is_ebcdic ) { qw(-Tcp1047) } + elsif( $self->_have_mandoc_with_utf8 ) { qw(-Tutf8) } + elsif( $self->_is_mandoc ) { qw() } + else { qw(-Tlatin1) } + } + +sub _is_roff { + my( $self ) = @_; + + $self->_is_nroff or $self->_is_groff; + } + +sub _is_nroff { + my( $self ) = @_; + + $self->__nroffer =~ /\bnroff\z/; + } + +sub _is_groff { + my( $self ) = @_; + + $self->__nroffer =~ /\bgroff\z/; + } + +sub _is_mandoc { + my ( $self ) = @_; + + $self->__nroffer =~ /\bmandoc\z/; + } + +sub _is_ebcdic { + my( $self ) = @_; + + return 0; + } + +sub _filter_through_nroff { + my( $self ) = shift; + $self->debug( "Filtering through " . $self->__nroffer() . "\n" ); + + my $render = $self->__nroffer() || $self->die( "no nroffer set!?" ); + my @render_switches = $self->_collect_nroff_switches; + $self->debug( "render is $render\n" ); + $self->debug( "render options are @render_switches\n" ); + + require Symbol; + require IPC::Open3; + require IO::Handle; + + my $pid = IPC::Open3::open3( + my $writer, + my $reader, + my $err = Symbol::gensym(), + $render, + @render_switches + ); + + $reader->autoflush(1); + + use IO::Select; + my $selector = IO::Select->new( $reader ); + + $self->debug( "Writing to pipe to $render\n" ); + + my $offset = 0; + my $chunk_size = 4096; + my $length = length( ${ $self->{_text_ref} } ); + my $chunks = $length / $chunk_size; + my $done; + my $buffer; + while( $offset <= $length ) { + $self->debug( "Writing chunk $chunks\n" ); $chunks++; + syswrite $writer, ${ $self->{_text_ref} }, $chunk_size, $offset + or $self->die( $! ); + $offset += $chunk_size; + $self->debug( "Checking read\n" ); + READ: { + last READ unless $selector->can_read( 0.01 ); + $self->debug( "Reading\n" ); + my $bytes = sysread $reader, $buffer, 4096; + $self->debug( "Read $bytes bytes\n" ); + $done .= $buffer; + $self->debug( sprintf "Output is %d bytes\n", + length $done + ); + next READ; + } + } + close $writer; + $self->debug( "Done writing\n" ); + + # read any leftovers + $done .= do { local $/; <$reader> }; + $self->debug( sprintf "Done reading. Output is %d bytes\n", + length $done + ); + + if( $? ) { + $self->warn( "Error from pipe to $render!\n" ); + $self->debug( 'Error: ' . do { local $/; <$err> } ); + } + + + close $reader; + if( my $err = $? ) { + $self->debug( + "Nonzero exit ($?) while running `$render @render_switches`.\n" . + "Falling back to Pod::Perldoc::ToPod\n" + ); + return $self->_fallback_to_pod( @_ ); + } + + $self->debug( "Output:\n----\n$done\n----\n" ); + + ${ $self->{_text_ref} } = $done; + + return length ${ $self->{_text_ref} } ? SUCCESS : FAILED; + } sub parse_from_file { - my $self = shift; - my($file, $outfh) = @_; - - my $render = $self->{'__nroffer'} || die "no nroffer set!?"; - - # turn the switches into CLIs - my $switches = join ' ', - map qq{"--$_=$self->{$_}"}, - grep !m/^_/s, - keys %$self - ; - - my $pod2man = - catfile( - ($self->{'__bindir'} || die "no bindir set?!" ), - ($self->{'__pod2man'} || die "no pod2man set?!" ), - ) - ; - unless(-e $pod2man) { - # This is rarely needed, I think. - $pod2man = $self->{'__pod2man'} || die "no pod2man set?!"; - die "Can't find a pod2man?! (". $self->{'__pod2man'} .")\nAborting" - unless -e $pod2man; - } - - my $command = "$pod2man $switches --lax $file | $render -man"; - # no temp file, just a pipe! - - # Thanks to Brendan O'Dea for contributing the following block - if(Pod::Perldoc::IS_Linux and -t STDOUT - and my ($cols) = `stty -a` =~ m/\bcolumns\s+(\d+)/ - ) { - my $c = $cols * 39 / 40; - $cols = $c > $cols - 2 ? $c : $cols -2; - $command .= ' -rLL=' . (int $c) . 'n' if $cols > 80; - } - - if(Pod::Perldoc::IS_Cygwin) { - $command .= ' -c'; - } - - # I hear persistent reports that adding a -c switch to $render - # solves many people's problems. But I also hear that some mans - # don't have a -c switch, so that unconditionally adding it here - # would presumably be a Bad Thing -- sburke@cpan.org - - $command .= " | col -x" if Pod::Perldoc::IS_HPUX; - - defined(&Pod::Perldoc::DEBUG) - and Pod::Perldoc::DEBUG() - and print "About to run $command\n"; - ; - - my $rslt = `$command`; - - my $err; - - if( $self->{'__filter_nroff'} ) { - defined(&Pod::Perldoc::DEBUG) - and &Pod::Perldoc::DEBUG() - and print "filter_nroff is set, so filtering...\n"; - $rslt = $self->___Do_filter_nroff($rslt); - } else { - defined(&Pod::Perldoc::DEBUG) - and Pod::Perldoc::DEBUG() - and print "filter_nroff isn't set, so not filtering.\n"; - } - - if (($err = $?)) { - defined(&Pod::Perldoc::DEBUG) - and Pod::Perldoc::DEBUG() - and print "Nonzero exit ($?) while running $command.\n", - "Falling back to Pod::Perldoc::ToPod\n ", - ; - # A desperate fallthru: - require Pod::Perldoc::ToPod; - return Pod::Perldoc::ToPod->new->parse_from_file(@_); - - } else { - print $outfh $rslt - or die "Can't print to $$self{__output_file}: $!"; - } - - return; -} - - -sub ___Do_filter_nroff { - my $self = shift; - my @data = split /\n{2,}/, shift; - - shift @data while @data and $data[0] !~ /\S/; # Go to header - shift @data if @data and $data[0] =~ /Contributed\s+Perl/; # Skip header - pop @data if @data and $data[-1] =~ /^\w/; # Skip footer, like - # 28/Jan/99 perl 5.005, patch 53 1 - join "\n\n", @data; -} + my( $self, $file, $outfh) = @_; + + # We have a pipeline of filters each affecting the reference + # in $self->{_text_ref} + $self->{_text_ref} = \my $output; + + $self->_parse_with_pod_man( $file ); + # so far, nroff is an external command so we ensure it worked + my $result = $self->_filter_through_nroff; + return $self->_fallback_to_pod( @_ ) unless $result == SUCCESS; + + $self->_post_nroff_processing; + + print { $outfh } $output or + $self->die( "Can't print to $$self{__output_file}: $!" ); + + return; + } + +sub _fallback_to_pod { + my( $self, @args ) = @_; + $self->warn( "Falling back to Pod because there was a problem!\n" ); + require Pod::Perldoc::ToPod; + return Pod::Perldoc::ToPod->new->parse_from_file(@_); + } + +# maybe there's a user setting we should check? +sub _get_tab_width { 4 } + +sub _expand_tabs { + my( $self ) = @_; + + my $tab_width = ' ' x $self->_get_tab_width; + + ${ $self->{_text_ref} } =~ s/\t/$tab_width/g; + } + +sub _post_nroff_processing { + my( $self ) = @_; + + if( $self->is_hpux ) { + $self->debug( "On HP-UX, I'm going to expand tabs for you\n" ); + # this used to be a pipe to `col -x` for HP-UX + $self->_expand_tabs; + } + + if( $self->{'__filter_nroff'} ) { + $self->debug( "filter_nroff is set, so filtering\n" ); + $self->_remove_nroff_header; + $self->_remove_nroff_footer; + } + else { + $self->debug( "filter_nroff is not set, so not filtering\n" ); + } + + $self->_handle_unicode; + + return 1; + } + +# I don't think this does anything since there aren't two consecutive +# newlines in the Pod::Man output +sub _remove_nroff_header { + my( $self ) = @_; + $self->debug( "_remove_nroff_header is still a stub!\n" ); + return 1; + +# my @data = split /\n{2,}/, shift; +# shift @data while @data and $data[0] !~ /\S/; # Go to header +# shift @data if @data and $data[0] =~ /Contributed\s+Perl/; # Skip header + } + +# I don't think this does anything since there aren't two consecutive +# newlines in the Pod::Man output +sub _remove_nroff_footer { + my( $self ) = @_; + $self->debug( "_remove_nroff_footer is still a stub!\n" ); + return 1; + ${ $self->{_text_ref} } =~ s/\n\n+.*\w.*\Z//m; + +# my @data = split /\n{2,}/, shift; +# pop @data if @data and $data[-1] =~ /^\w/; # Skip footer, like + # 28/Jan/99 perl 5.005, patch 53 1 + } + +sub _unicode_already_handled { + my( $self ) = @_; + + $self->_have_groff_with_utf8 || + 1 # so, we don't have a case that needs _handle_unicode + ; + } + +sub _handle_unicode { +# this is the job of preconv +# we don't need this with groff 1.20 and later. + my( $self ) = @_; + + return 1 if $self->_unicode_already_handled; + + require Encode; + + # it's UTF-8 here, but we need character data + my $text = Encode::decode( 'UTF-8', ${ $self->{_text_ref} } ) ; + +# http://www.mail-archive.com/groff@gnu.org/msg01378.html +# http://linux.die.net/man/7/groff_char +# http://www.gnu.org/software/groff/manual/html_node/Using-Symbols.html +# http://lists.gnu.org/archive/html/groff/2011-05/msg00007.html +# http://www.simplicidade.org/notes/archives/2009/05/fixing_the_pod.html +# http://lists.freebsd.org/pipermail/freebsd-questions/2011-July/232239.html + $text =~ s/(\P{ASCII})/ + sprintf '\\[u%04X]', ord $1 + /eg; + + # should we encode? + ${ $self->{_text_ref} } = $text; + } 1; @@ -149,7 +509,7 @@ Pod::Perldoc::ToMan - let Perldoc render Pod as man pages =head1 DESCRIPTION This is a "plug-in" class that allows Perldoc to use -Pod::Man and C<nroff> for reading Pod pages. +Pod::Man and C<groff> for reading Pod pages. The following options are supported: center, date, fixed, fixedbold, fixeditalic, fixedbolditalic, quotes, release, section @@ -171,6 +531,8 @@ L<Pod::Man>, L<Pod::Perldoc>, L<Pod::Perldoc::ToNroff> =head1 COPYRIGHT AND DISCLAIMERS +Copyright (c) 2011 brian d foy. All rights reserved. + Copyright (c) 2002,3,4 Sean M. Burke. All rights reserved. This library is free software; you can redistribute it and/or modify it @@ -182,10 +544,12 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToNroff.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToNroff.pm index 991c1e3269..e888d75d85 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToNroff.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToNroff.pm @@ -1,12 +1,12 @@ - -require 5; package Pod::Perldoc::ToNroff; use strict; use warnings; +use parent qw(Pod::Perldoc::BaseTo); -# This is unlike ToMan.pm in that it emits the raw nroff source! +use vars qw($VERSION); +$VERSION = '3.15_15'; -use base qw(Pod::Perldoc::BaseTo); +# This is unlike ToMan.pm in that it emits the raw nroff source! sub is_pageable { 1 } # well, if you ask for it... sub write_with_binmode { 0 } @@ -29,13 +29,13 @@ sub new { return bless {}, ref($_[0]) || $_[0] } sub parse_from_file { my $self = shift; my $file = $_[0]; - + my @options = map {; $_, $self->{$_} } grep !m/^_/s, keys %$self ; - + defined(&Pod::Perldoc::DEBUG) and Pod::Perldoc::DEBUG() and print "About to call new Pod::Man ", @@ -94,10 +94,12 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToPod.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToPod.pm index c3173d4370..f5c9b6658a 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToPod.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToPod.pm @@ -1,18 +1,11 @@ - -# This class is just a hack to act as a "formatter" for -# actually unformatted Pod. -# -# Note that this isn't the same as just passing thru whatever -# we're given -- we pass thru only the pod source, and suppress -# the Perl code (or whatever non-pod stuff is in the source file). - - -require 5; package Pod::Perldoc::ToPod; use strict; use warnings; +use parent qw(Pod::Perldoc::BaseTo); + +use vars qw($VERSION); +$VERSION = '3.15_15'; -use base qw(Pod::Perldoc::BaseTo); sub is_pageable { 1 } sub write_with_binmode { 0 } sub output_extension { 'pod' } @@ -22,10 +15,10 @@ sub new { return bless {}, ref($_[0]) || $_[0] } sub parse_from_file { my( $self, $in, $outfh ) = @_; - open(IN, "<", $in) or die "Can't read-open $in: $!\nAborting"; + open(IN, "<", $in) or $self->die( "Can't read-open $in: $!\nAborting" ); my $cut_mode = 1; - + # A hack for finding things between =foo and =cut, inclusive local $_; while (<IN>) { @@ -37,10 +30,10 @@ sub parse_from_file { } } next if $cut_mode; - print $outfh $_ or die "Can't print to $outfh: $!"; + print $outfh $_ or $self->die( "Can't print to $outfh: $!" ); } - - close IN or die "Can't close $in: $!"; + + close IN or $self->die( "Can't close $in: $!" ); return; } @@ -84,10 +77,12 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallencpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToRtf.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToRtf.pm index 14d419fc31..2aa8cdcd3e 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToRtf.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToRtf.pm @@ -1,17 +1,10 @@ - -require 5; package Pod::Perldoc::ToRtf; use strict; use warnings; -use vars qw($VERSION); - -use base qw( Pod::Simple::RTF ); - -$VERSION # so that ->VERSION is happy -# stop CPAN from seeing this - = -$Pod::Simple::RTF::VERSION; +use parent qw( Pod::Simple::RTF ); +use vars qw($VERSION); +$VERSION = '3.15_15'; sub is_pageable { 0 } sub write_with_binmode { 0 } @@ -20,11 +13,11 @@ sub output_extension { 'rtf' } sub page_for_perldoc { my($self, $tempfile, $perldoc) = @_; return unless $perldoc->IS_MSWin32; - + my $rtf_pager = $ENV{'RTFREADER'} || 'write.exe'; - + $perldoc->aside( "About to launch <\"$rtf_pager\" \"$tempfile\">\n" ); - + return 1 if system( qq{"$rtf_pager"}, qq{"$tempfile"} ) == 0; return 0; } @@ -79,10 +72,12 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToTerm.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToTerm.pm new file mode 100644 index 0000000000..c2c541ee84 --- /dev/null +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToTerm.pm @@ -0,0 +1,90 @@ +package Pod::Perldoc::ToTerm; +use strict; +use warnings; + +use vars qw($VERSION); +$VERSION = '3.15_15'; + +use parent qw(Pod::Perldoc::BaseTo); + +sub is_pageable { 1 } +sub write_with_binmode { 0 } +sub output_extension { 'txt' } + +use Pod::Text::Termcap (); + +sub alt { shift->_perldoc_elem('alt' , @_) } +sub indent { shift->_perldoc_elem('indent' , @_) } +sub loose { shift->_perldoc_elem('loose' , @_) } +sub quotes { shift->_perldoc_elem('quotes' , @_) } +sub sentence { shift->_perldoc_elem('sentence', @_) } +sub width { shift->_perldoc_elem('width' , @_) } + +sub new { return bless {}, ref($_[0]) || $_[0] } + +sub parse_from_file { + my $self = shift; + + my @options = + map {; $_, $self->{$_} } + grep !m/^_/s, + keys %$self + ; + + defined(&Pod::Perldoc::DEBUG) + and Pod::Perldoc::DEBUG() + and print "About to call new Pod::Text::Termcap ", + $Pod::Text::VERSION ? "(v$Pod::Text::VERSION) " : '', + "with options: ", + @options ? "[@options]" : "(nil)", "\n"; + ; + + Pod::Text::Termcap->new(@options)->parse_from_file(@_); +} + +1; + +=head1 NAME + +Pod::Perldoc::ToTerm - render Pod with terminal escapes + +=head1 SYNOPSIS + + perldoc -o term Some::Modulename + +=head1 DESCRIPTION + +This is a "plug-in" class that allows Perldoc to use +Pod::Text as a formatter class. + +It supports the following options, which are explained in +L<Pod::Text>: alt, indent, loose, quotes, sentence, width + +For example: + + perldoc -o term -w indent:5 Some::Modulename + +=head1 CAVEAT + +This module may change to use a different text formatter class in the +future, and this may change what options are supported. + +=head1 SEE ALSO + +L<Pod::Text>, L<Pod::Text::Termcap>, L<Pod::Perldoc> + +=head1 COPYRIGHT AND DISCLAIMERS + +Copyright (c) 2011 Mark Allen. + +This program is free software; you can redistribute it and/or modify it +under the terms of either: the GNU General Public License as published +by the Free Software Foundation; or the Artistic License. + +See http://dev.perl.org/licenses/ for more information. + +=head1 AUTHOR + +Mark Allen C<< <mallen@cpan.org> >> + +=cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToText.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToText.pm index 7d1784cd59..bfde85f427 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToText.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToText.pm @@ -1,10 +1,11 @@ - -require 5; package Pod::Perldoc::ToText; use strict; use warnings; -use base qw(Pod::Perldoc::BaseTo); +use vars qw($VERSION); +$VERSION = '3.15_15'; + +use parent qw(Pod::Perldoc::BaseTo); sub is_pageable { 1 } sub write_with_binmode { 0 } @@ -23,13 +24,13 @@ sub new { return bless {}, ref($_[0]) || $_[0] } sub parse_from_file { my $self = shift; - + my @options = map {; $_, $self->{$_} } grep !m/^_/s, keys %$self ; - + defined(&Pod::Perldoc::DEBUG) and Pod::Perldoc::DEBUG() and print "About to call new Pod::Text ", @@ -85,10 +86,12 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToTk.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToTk.pm index 5b29fd996e..9072150058 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToTk.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToTk.pm @@ -1,10 +1,11 @@ - -require 5; package Pod::Perldoc::ToTk; use strict; use warnings; -use base qw(Pod::Perldoc::BaseTo); +use vars qw($VERSION); +$VERSION = '3.15_15'; + +use parent qw(Pod::Perldoc::BaseTo); sub is_pageable { 1 } sub write_with_binmode { 0 } @@ -20,12 +21,30 @@ sub forky { shift->_perldoc_elem('forky' , @_) } use Pod::Perldoc (); use File::Spec::Functions qw(catfile); -use Tk; -die join '', __PACKAGE__, " doesn't work nice with Tk.pm version $Tk::VERSION" - if $Tk::VERSION eq '800.003'; +BEGIN{ # Tk is not core, but this is + eval { require Tk } || + __PACKAGE__->die( <<"HERE" ); +You must have the Tk module to use Pod::Perldoc::ToTk. +If you have it installed, ensure it's in your Perl library +path. +HERE + + __PACKAGE__->die( + __PACKAGE__, + " doesn't work nice with Tk.pm version $Tk::VERSION" + ) if $Tk::VERSION eq '800.003'; + } + BEGIN { eval { require Tk::FcyEntry; }; }; -use Tk::Pod; +BEGIN{ # Tk::Pod is not core, but this is + eval { require Tk::Pod } || + __PACKAGE__->die( <<"HERE" ); +You must have the Tk::Pod module to use Pod::Perldoc::ToTk. +If you have it installed, ensure it's in your Perl library +path. +HERE + } # The following was adapted from "tkpod" in the Tk-Pod dist. @@ -35,29 +54,29 @@ sub parse_from_file { if($self->{'forky'}) { return if fork; # i.e., parent process returns } - + $Input_File =~ s{\\}{/}g - if Pod::Perldoc::IS_MSWin32 or Pod::Perldoc::IS_Dos + if $self->is_mswin32 or $self->is_dos # and maybe OS/2 ; - + my($tk_opt, $tree); $tree = $self->{'tree' }; $tk_opt = $self->{'tk_opt'}; - + #require Tk::ErrorDialog; - + # Add 'Tk' subdirectories to search path so, e.g., # 'Scrolled' will find doc in 'Tk/Scrolled' - + if( $tk_opt ) { push @INC, grep -d $_, map catfile($_,'Tk'), @INC; } - + my $mw = MainWindow->new(); #eval 'use blib "/home/e/eserte/src/perl/Tk-App";require Tk::App::Debug'; $mw->withdraw; - + # CDE use Font Settings if available my $ufont = $mw->optionGet('userFont','UserFont'); # fixed width my $sfont = $mw->optionGet('systemFont','SystemFont'); # proportional @@ -67,18 +86,18 @@ sub parse_from_file { $mw->optionAdd('*Entry.Font', $ufont); $mw->optionAdd('*Text.Font', $ufont); } - + $mw->optionAdd('*Menu.tearOff', $Tk::platform ne 'MSWin32' ? 1 : 0); - + $mw->Pod( '-file' => $Input_File, (($Tk::Pod::VERSION >= 4) ? ('-tree' => $tree) : ()) )->focusNext; - + # xxx dirty but it works. A simple $mw->destroy if $mw->children # does not work because Tk::ErrorDialogs could be created. # (they are withdrawn after Ok instead of destory'ed I guess) - + if ($mw->children) { $mw->repeat(1000, sub { # ErrorDialog is withdrawn not deleted :-( @@ -122,10 +141,13 @@ L<Tk::Pod>, L<Pod::Perldoc> =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke C<sburke@cpan.org>, with significant portions copied from +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>; +Sean M. Burke C<< <sburke@cpan.org> >>; +significant portions copied from F<tkpod> in the Tk::Pod dist, by Nick Ing-Simmons, Slaven Rezic, et al. =cut diff --git a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToXml.pm b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToXml.pm index 439e736c20..19875a556b 100644 --- a/dist/Pod-Perldoc/lib/Pod/Perldoc/ToXml.pm +++ b/dist/Pod-Perldoc/lib/Pod/Perldoc/ToXml.pm @@ -1,17 +1,12 @@ - -require 5; package Pod::Perldoc::ToXml; use strict; use warnings; use vars qw($VERSION); -use base qw( Pod::Simple::XMLOutStream ); - -$VERSION # so that ->VERSION is happy -# stop CPAN from seeing this - = -$Pod::Simple::XMLOutStream::VERSION; +use parent qw( Pod::Simple::XMLOutStream ); +use vars qw($VERSION); +$VERSION = '3.15_15'; sub is_pageable { 0 } sub write_with_binmode { 0 } @@ -57,10 +52,12 @@ merchantability or fitness for a particular purpose. =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributions from: -Sean M. Burke <sburke@cpan.org> +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >> =cut diff --git a/dist/Pod-Perldoc/lib/perldoc.pod b/dist/Pod-Perldoc/lib/perldoc.pod index 6a45148c60..42a9eab4cd 100644 --- a/dist/Pod-Perldoc/lib/perldoc.pod +++ b/dist/Pod-Perldoc/lib/perldoc.pod @@ -5,34 +5,36 @@ perldoc - Look up Perl documentation in Pod format. =head1 SYNOPSIS -B<perldoc> [B<-h>] [B<-D>] [B<-t>] [B<-u>] [B<-m>] [B<-l>] [B<-F>] -[B<-i>] [B<-V>] [B<-T>] [B<-r>] -[B<-dI<destination_file>>] -[B<-oI<formatname>>] -[B<-MI<FormatterClassName>>] -[B<-wI<formatteroption:value>>] -[B<-n>I<nroff-replacement>] -[B<-X>] -[B<-L> I<language_code>] -PageName|ModuleName|ProgramName|URL + B<perldoc> [B<-h>] [B<-D>] [B<-t>] [B<-u>] [B<-m>] [B<-l>] [B<-F>] + [B<-i>] [B<-V>] [B<-T>] [B<-r>] + [B<-dI<destination_file>>] + [B<-oI<formatname>>] + [B<-MI<FormatterClassName>>] + [B<-wI<formatteroption:value>>] + [B<-n>I<nroff-replacement>] + [B<-X>] + [B<-L> I<language_code>] + PageName|ModuleName|ProgramName|URL -B<perldoc> B<-f> BuiltinFunction +Examples: + + B<perldoc> B<-f> BuiltinFunction -B<perldoc> B<-L> it B<-f> BuiltinFunction + B<perldoc> B<-L> it B<-f> BuiltinFunction -B<perldoc> B<-q> FAQ Keyword + B<perldoc> B<-q> FAQ Keyword -B<perldoc> B<-L> fr B<-q> FAQ Keyword + B<perldoc> B<-L> fr B<-q> FAQ Keyword -B<perldoc> B<-v> PerlVariable + B<perldoc> B<-v> PerlVariable See below for more description of the switches. =head1 DESCRIPTION -I<perldoc> looks up a piece of documentation in .pod format that is embedded -in the perl installation tree or in a perl script, and displays it via -C<pod2man | nroff -man | $PAGER>. (In addition, if running under HP-UX, +B<perldoc> looks up a piece of documentation in .pod format that is +embedded in the perl installation tree or in a perl script, and displays +it via C<groff -man | $PAGER>. (In addition, if running under HP-UX, C<col -x> will be used.) This is primarily used for the documentation for the perl library modules. @@ -193,7 +195,7 @@ So "perldoc intro" is enough to find/render "perlintro.pod". =item B<-n> I<some-formatter> -Specify replacement for nroff +Specify replacement for groff =item B<-r> @@ -209,8 +211,6 @@ Displays the version of perldoc you're running. =back - - =head1 SECURITY Because B<perldoc> does not run properly tainted, and is known to @@ -259,12 +259,14 @@ L<perlpod>, L<Pod::Perldoc> =head1 AUTHOR -Current maintainer: Adriano R. Ferreira <ferreira@cpan.org> +Current maintainer: Mark Allen C<< <mallen@cpan.org> >> Past contributors are: -Sean M. Burke <sburke@cpan.org>, -Kenneth Albanowski <kjahds@kjahds.com>, -Andy Dougherty <doughera@lafcol.lafayette.edu>, +brian d foy C<< <bdfoy@cpan.org> >> +Adriano R. Ferreira C<< <ferreira@cpan.org> >>, +Sean M. Burke C<< <sburke@cpan.org> >>, +Kenneth Albanowski C<< <kjahds@kjahds.com> >>, +Andy Dougherty C<< <doughera@lafcol.lafayette.edu> >>, and many others. =cut diff --git a/dist/Pod-Perldoc/t/01_about_verbose.t b/dist/Pod-Perldoc/t/01_about_verbose.t deleted file mode 100644 index 6a0f30eabd..0000000000 --- a/dist/Pod-Perldoc/t/01_about_verbose.t +++ /dev/null @@ -1,86 +0,0 @@ - -require 5; -# Time-stamp: "2004-04-09 18:02:36 ADT" - -# Summary of, well, things. - -use Test::More tests => 2; - -BEGIN { - use_ok 'Pod::Perldoc'; -} - -#chdir "t" if -e "t"; - -{ - my @out; - push @out, - "\n\nPerl v", - defined($^V) ? sprintf('%vd', $^V) : $], - " under $^O ", - (defined(&Win32::BuildNumber) and defined &Win32::BuildNumber()) - ? ("(Win32::BuildNumber ", &Win32::BuildNumber(), ")") : (), - (defined $MacPerl::Version) - ? ("(MacPerl version $MacPerl::Version)") : (), - "\n" - ; - - # Ugly code to walk the symbol tables: - my %v; - my @stack = (''); # start out in %:: - my $this; - my $count = 0; - my $pref; - while(@stack) { - $this = shift @stack; - die "Too many packages?" if ++$count > 1000; - next if exists $v{$this}; - next if $this eq 'main'; # %main:: is %:: - - #print "Peeking at $this => ${$this . '::VERSION'}\n"; - - if(defined ${$this . '::VERSION'} ) { - $v{$this} = ${$this . '::VERSION'} - } elsif( - defined *{$this . '::ISA'} or defined &{$this . '::import'} - or ($this ne '' and grep defined *{$_}{'CODE'}, values %{$this . "::"}) - # If it has an ISA, an import, or any subs... - ) { - # It's a class/module with no version. - $v{$this} = undef; - } else { - # It's probably an unpopulated package. - ## $v{$this} = '...'; - } - - $pref = length($this) ? "$this\::" : ''; - push @stack, map m/^(.+)::$/ ? "$pref$1" : (), keys %{$this . '::'}; - #print "Stack: @stack\n"; - } - push @out, " Modules in memory:\n"; - delete @v{'', '[none]'}; - foreach my $p (sort {lc($a) cmp lc($b)} keys %v) { - $indent = ' ' x (2 + ($p =~ tr/:/:/)); - push @out, ' ', $indent, $p, defined($v{$p}) ? " v$v{$p};\n" : ";\n"; - } - push @out, sprintf "[at %s (local) / %s (GMT)]\n", - scalar(gmtime), scalar(localtime); - my $x = join '', @out; - $x =~ s/^/#/mg; - print $x; -} - -print "# Running", - (chr(65) eq 'A') ? " in an ASCII world.\n" : " in a non-ASCII world.\n", - "#\n", -; - -print "# \@INC:\n", map("# [$_]\n", @INC), "#\n#\n"; - -print "# \%INC:\n"; -foreach my $x (sort {lc($a) cmp lc($b)} keys %INC) { - print "# [$x] = [", $INC{$x} || '', "]\n"; -} - -pass(); - diff --git a/dist/Pod-Perldoc/t/checkerbasic.t b/dist/Pod-Perldoc/t/checkerbasic.t deleted file mode 100644 index a8d4dc0113..0000000000 --- a/dist/Pod-Perldoc/t/checkerbasic.t +++ /dev/null @@ -1,8 +0,0 @@ - -use Test::More tests => 2; -pass(); -require Pod::Perldoc::ToChecker; -$Pod::Perldoc::VERSION - and print "# Pod::Perldoc version $Pod::Perldoc::VERSION\n"; -pass(); - diff --git a/dist/Pod-Perldoc/t/load.t b/dist/Pod-Perldoc/t/load.t new file mode 100644 index 0000000000..f1a2ef9f4f --- /dev/null +++ b/dist/Pod-Perldoc/t/load.t @@ -0,0 +1,23 @@ +use strict; +use warnings; + +use Test::More; + +my @classes = ('Pod::Perldoc', map { "Pod::Perldoc::$_" } qw( + BaseTo ToChecker ToNroff ToRtf + GetOptsOO ToMan ToPod ToText ToXml + ToANSI ToTerm +) ); + +if( eval { require Tk; require Tk::Pod; 1 } ) { push @classes, 'Pod::Perldoc::ToTk' } +else { + diag "Skip testing Pod::Perldoc::ToTk because there's no Tk"; + } + +plan tests => scalar @classes; + +foreach my $class ( @classes ) { + require_ok( $class ); + my $version = do { no strict 'refs'; ${ '$' . $class . '::VERSION' } }; + diag( "$class $version" ) if defined $version + } diff --git a/dist/Pod-Perldoc/t/man/_get_columns.t b/dist/Pod-Perldoc/t/man/_get_columns.t new file mode 100644 index 0000000000..e2f870bc26 --- /dev/null +++ b/dist/Pod-Perldoc/t/man/_get_columns.t @@ -0,0 +1,68 @@ +use Test::More; +use strict; +use warnings; + +{ +package Local::ToMan; +use base 'Pod::Perldoc::ToMan'; +use vars qw( $stty_text $is_linux $warning ); +no warnings 'redefine'; +no strict 'refs'; +sub _get_stty { $stty_text } +sub is_linux { $is_linux } +sub warn { shift; $warning = join '', @_ } +} + +BEGIN { +our @columns = qw( EXPECTED IS_LINUX MANWIDTH MANWIDTH_EXPECTED STTY STTY_EXPECTED ); +foreach my $i ( 0 .. $#columns ) { + no strict 'refs'; + *{"$columns[$i]"} = sub () { $i }; + } +} + +my @tests = ( + # for linux, choose between manwidth and stty + [ 62, 1, undef, 0, "; 62 columns;", 62 ], + [ 63, 1, undef, 0, "columns 63", 63 ], + [ 57, 1, 57, 57, "columns 63", 63 ], + [ 73, 1, undef, 0, " ", 0 ], + + # for not linux, the same + [ 62, 0, undef, 0, "; 62 columns;", 62 ], + [ 63, 0, undef, 0, "columns 63", 63 ], + [ 57, 0, 57, 57, "columns 63", 63 ], + [ 73, 0, undef, 0, " ", 0 ], + + # bad manwidths + [ 62, 1, -1, 0, "; 62 columns;", 62 ], + [ 63, 1, 'abc', 0, "columns 63", 63 ], + [ 64, 1, '', 0, "columns 64", 64 ], + [ 73, 1, undef, 0, " ", 0 ], + ); + +plan tests => 3 * @tests; + + +foreach my $test ( @tests ) { + local $ENV{MANWIDTH} = $test->[MANWIDTH]; + local $Local::ToMan::stty_text = $test->[STTY]; + local $Local::ToMan::is_linux = $test->[IS_LINUX]; + + { + no warnings 'uninitialized'; + diag( sprintf + "MANWIDTH: %s STTY: %s LINUX: %s", + defined $ENV{MANWIDTH} ? $ENV{MANWIDTH} : "(undef)", + $Local::ToMan::stty_text, + $Local::ToMan::is_linux, + ) if $ENV{PERLDOCDEBUG}; + } + + is( Local::ToMan->_get_columns_from_manwidth(), $test->[MANWIDTH_EXPECTED], + "_get_columns_from_manwidth returns the right number" ); + is( Local::ToMan->_get_columns_from_stty(), $test->[STTY_EXPECTED], + "_get_columns_from_stty returns the right number" ); + is( Local::ToMan->_get_columns, $test->[EXPECTED], + "_get_columns returns the right number" ); + } diff --git a/dist/Pod-Perldoc/t/perldocbasic.t b/dist/Pod-Perldoc/t/perldocbasic.t deleted file mode 100644 index e11b91e78e..0000000000 --- a/dist/Pod-Perldoc/t/perldocbasic.t +++ /dev/null @@ -1,8 +0,0 @@ - -use Test::More tests => 3; -pass(); -require Pod::Perldoc; -ok($Pod::Perldoc::VERSION) - and print "# Pod::Perldoc version $Pod::Perldoc::VERSION\n"; -pass(); - diff --git a/dist/Pod-Perldoc/t/pod.t b/dist/Pod-Perldoc/t/pod.t new file mode 100644 index 0000000000..3dbee4f436 --- /dev/null +++ b/dist/Pod-Perldoc/t/pod.t @@ -0,0 +1,11 @@ +use strict; +use warnings; +use Test::More; + +unless ( $ENV{RELEASE_TESTING} ) { + plan skip_all => 'Pod tests not required for installation.'; +} + +eval "use Test::Pod 1.22"; +plan skip_all => 'Test::Pod 1.22 or higher not installed.' if $@; +all_pod_files_ok(); diff --git a/dist/Pod-Perldoc/t/textbasic.t b/dist/Pod-Perldoc/t/textbasic.t deleted file mode 100644 index 3ed19a3452..0000000000 --- a/dist/Pod-Perldoc/t/textbasic.t +++ /dev/null @@ -1,8 +0,0 @@ - -use Test::More tests => 2; -pass(); -require Pod::Perldoc::ToText; -$Pod::Perldoc::VERSION - and print "# Pod::Perldoc version $Pod::Perldoc::VERSION\n"; -pass(); - |