parallel: small optimization for --pipe

doc/FUTURE_IDEAS

@@ -1,3 +1,17 @@
+Postkort:
+- Forside kun figur
+- Bagside:
+  - Logo med figur - evt gnu.org/s/parallel
+  - kort grå tekst, der forklarer hvad det er.
+  - Eet eksempel: parallel gzip ::: *
+  - Link til video. http://nd.gd/0s 
+
+GNU parallel is a UNIX-tool for running commands in parallel.
+To gzip all files running one job per CPU write:
+  parallel gzip ::: *
+Watch the intro video to learn more: http://nd.gd/0s
+Or read more about GNU parallel: www.gnu.org/s/parallel
+
 job->start():
 $jobslot = Global::jobslot->$sshlogin
 

doc/release_new_version

@@ -158,9 +158,9 @@ cc:Peter Simons <simons@cryp.to>, Sandro Cazzaniga <kharec@mandriva.org>,
    Christian Faulhammer <fauli@gentoo.org>, Ryoichiro Suzuki <ryoichiro.suzuki@gmail.com>,
    Jesse Alama <jesse.alama@gmail.com>
 
-Subject: GNU Parallel 2011XXXX ('?') released
+Subject: GNU Parallel 2011XX22 ('Pakistan') released
 
-GNU Parallel 2011XXXX ('?') has been released. It is
+GNU Parallel 2011XX22 ('Pakistan') has been released. It is
 available for download at: http://ftp.gnu.org/gnu/parallel/
 
 New in this release:
@@ -173,6 +173,12 @@ New in this release:
 * Review with idea for {..} and {...} in Japanese. Thanks to ichii386.
   http://d.hatena.ne.jp/ichii386/20110426
 
+* Upgrade GNU Parallel using Macports. Thanks to Phil Hollenback.
+  http://www.hollenback.net/index.php/MacportsParallel
+
+* Robert from Echo One discusses using processes instead of threads:
+  http://rrees.wordpress.com/2011/04/25/many-cores-many-threads/
+
 * Bug fixes and man page updates.
 
 

src/parallel

@@ -108,12 +108,20 @@ sub spreadstdin {
 	$recerror = "parallel: Warning: --recend unmatched. Is --blocksize too small?";
     }
 
-    while(read(STDIN,substr($buf,length $buf,0),$::opt_blocksize)) {
-	# substr above = append to $buf
     if($::opt_regexp) {
 	# If $recstart/$recend contains '|' this should only apply to the regexp
 	$recstart = "(?:".$recstart.")";
 	$recend = "(?:".$recend.")";
+    } else {
+	# $recstart/$recend = printf strings (\n)
+	$recstart =~ s/\\([rnt'"\\])/"qq|\\$1|"/gee;
+	$recend =~ s/\\([rnt'"\\])/"qq|\\$1|"/gee;
+    }
+    my $recendrecstart = $recend.$recstart;
+
+    while(read(STDIN,substr($buf,length $buf,0),$::opt_blocksize)) {
+	# substr above = append to $buf
+	if($::opt_regexp) {
 	    if($Global::max_number_of_args) {
 		# -N => (start..*?end){n}
 		while($buf =~ s/((?:$recstart.*?$recend){$Global::max_number_of_args})($recstart.*)$/$2/os) {
@@ -130,13 +138,10 @@ sub spreadstdin {
 		}
 	    }
 	} else {
-	    # $recstart/$recend = printf strings (\n)
-	    $recstart =~ s/\\([rnt'"\\])/"qq|\\$1|"/gee;
-	    $recend =~ s/\\([rnt'"\\])/"qq|\\$1|"/gee;
 	    if($Global::max_number_of_args) {
 		# -N => (start..*?end){n}
 		my $i = 0;
-		while(($i = nindex(\$buf,$recend.$recstart,$Global::max_number_of_args)) != -1) {
+		while(($i = nindex(\$buf,$recendrecstart,$Global::max_number_of_args)) != -1) {
 		    $i += length $recend; # find the actual splitting location
 		    my $record = substr($buf,0,$i);
 		    substr($buf,0,$i) = "";
@@ -145,7 +150,7 @@ sub spreadstdin {
 		}
 	    } else {
 		# Find the last recend-recstart in $buf
-		my $i = rindex($buf,$recend.$recstart);
+		my $i = rindex($buf,$recendrecstart);
 		if($i != -1) {
 		    $i += length $recend; # find the actual splitting location
 		    my $record = substr($buf,0,$i);

src/parallel.pod

@@ -1415,6 +1415,26 @@ can be written like this:
 B<cat list | parallel "do_something {} scale {.}.jpg ; do_step2 <{} {.}" | process_output>
 
 
+=head1 EXAMPLE: Rewriting nested for-loops
+
+Nested for-loops like this:
+
+  (for x in `cat xlist` ; do
+    for y in `cat ylist` ; do
+      do_something $x $y
+    done
+  done) | process_output
+
+can be written like this:
+
+B<cat xlist | parallel cat ylist \| parallel -I {o} do_something {} {o} | process_output>
+
+The above will run N*N jobs in parallel if parallel normally runs N jobs. To
+ensure the output order is the same as the input and only run N jobs do:
+
+B<cat xlist | parallel -k cat ylist \| parallel -j1 -kI {o} do_something {} {o} | process_output>
+
+
 =head1 EXAMPLE: Group output lines
 
 When running jobs that output data, you often do not want the output
@@ -1501,8 +1521,8 @@ B<cat bigfile | parallel --pipe --block 10M grep foo>
 =head1 EXAMPLE: Using remote computers
 
 To run commands on a remote computer SSH needs to be set up and you
-must be able to login without entering a password (B<ssh-agent> may be
-handy).
+must be able to login without entering a password (The commands
+B<ssh-copy-id> and B<ssh-agent> may help you do that).
 
 To run B<echo> on B<server.example.com>:
 
@@ -1643,6 +1663,8 @@ Print the number on the opposing sides of a six sided die:
 
 B<parallel -a <(seq 6) -a <(seq 6 -1 1) echo>
 
+B<parallel echo :::: <(seq 6) <(seq 6 -1 1)>
+
 Convert files from all subdirs to PNG-files with consecutive numbers
 (useful for making input PNG's for B<ffmpeg>):
 
@@ -1693,12 +1715,12 @@ job. wget is too - if the webpages are small.
 The content of the file jobs_to_run:
 
   ping -c 1 10.0.0.1
-  wget http://status-server/status.cgi?ip=10.0.0.1
+  wget http://example.com/status.cgi?ip=10.0.0.1
   ping -c 1 10.0.0.2
-  wget http://status-server/status.cgi?ip=10.0.0.2
+  wget http://example.com/status.cgi?ip=10.0.0.2
   ...
   ping -c 1 10.0.0.255
-  wget http://status-server/status.cgi?ip=10.0.0.255
+  wget http://example.com/status.cgi?ip=10.0.0.255
 
 To run 100 processes simultaneously do: