parallel: {0%}/{0#} zero-padded jobslot/sequence number.

This commit is contained in:
Ole Tange 2021-02-20 22:47:31 +01:00
parent fff769f675
commit b46e90b7c5
5 changed files with 82 additions and 32 deletions

View file

@ -2212,6 +2212,12 @@ sub init_globals() {
'{choose_k}' => 'for $t (2..$#arg){ if($arg[$t-1] ge $arg[$t]) { skip() } }',
# {##} = number of jobs
'{##}' => '$_=total_jobs()',
# {0%} = 0-padded jobslot
'{0%}' => '$f=1+int((log($Global::max_jobs_running||1)/log(10))); $_=sprintf("%0${f}d",slot())',
# {0%} = 0-padded seq
'{0#}' => '$f=1+int((log(total_jobs())/log(10))); $_=sprintf("%0${f}d",seq())',
## Bash inspired replacement strings
# Bash ${a:-myval}
'{:-([^}]+?)}' => '$_ ||= $$1',
# Bash ${a:2}
@ -6301,6 +6307,7 @@ sub set_max_jobs_running($$) {
$Global::max_jobs_running -= $self->{'max_jobs_running'};
}
$self->{'max_jobs_running'} = shift;
if(defined $self->{'max_jobs_running'}) {
# max_jobs_running could be resat if -j is a changed file
$Global::max_jobs_running += $self->{'max_jobs_running'};
@ -10811,12 +10818,13 @@ sub new($) {
sub flush_cache() {
my $self = shift;
for my $arglist (@{$self->{'arglist'}}) {
for my $arglist (@{$self->{'arg_list'}}) {
for my $arg (@$arglist) {
$arg->flush_cache();
}
}
$self->{'arg_queue'}->flush_cache();
$self->{'replaced'} = undef;
}
sub seq($) {
@ -13657,6 +13665,7 @@ sub main() {
# Compute $Global::max_jobs_running
# Must be done after ungetting any --pipepart jobs.
max_jobs_running();
init_run_jobs();
my $sem;
if($Global::semaphore) {

View file

@ -299,14 +299,20 @@ directory (if any) and extension removed.
To understand positional replacement strings see B<{>I<n>B<}>.
=item B<{=>I<perl expression>B<=}>
=item B<{=>I<perl expression>B<=}> (alpha testing)
Replace with calculated I<perl expression>. B<$_> will contain the
same as B<{}>. After evaluating I<perl expression> B<$_> will be used
as the value. It is recommended to only change $_ but you have full
access to all of GNU B<parallel>'s internal functions and data
structures. A few convenience functions and data structures have been
made:
structures.
The expression must give the same result if evaluated twice -
otherwise the behaviour is undefined. E.g. this will not work as expected:
parallel echo '{= $_= ++$wrong_counter =}' ::: a b c
A few convenience functions and data structures have been made:
=over 15
@ -870,7 +876,7 @@ replacement strings and Perl code. Example:
parallel --filter '{1} < {2}+1' echo ::: {1..3} ::: {1..3}
Runs: 1,1 1,2 1,3 2,2 2,3 3,3
Outputs: 1,1 1,2 1,3 2,2 2,3 3,3
=item B<--filter-hosts>
@ -1625,11 +1631,9 @@ Activate additional replacement strings: {+/} {+.} {+..} {+...} {..}
B<{##}> is the total number of jobs to be run. It is incompatible with
B<-X>/B<-m>/B<--xargs>.
B<{0%}>, B<{00%}>, B<{000%}>, ... B<{0..0%}> prefix jobslot with
zeros. (alpha testing)
B<{0%}> zero-padded jobslot. (alpha testing)
B<{0#}>, B<{00#}>, B<{000#}>, ... B<{0..0#}> prefix sequence numbers
with zeros. (alpha testing)
B<{0#}> zero-padded sequence number. (alpha testing)
B<{choose_k}> is inspired by n choose k: Given a list of n elements,
choose k. k is the number of input sources and n is the number of
@ -2640,6 +2644,23 @@ will be replaced.
With B<--cleanup> the new file will be removed when the job is done.
If I<my.tmpl> contains this:
Xval: {x}
Yval: {y}
FixedValue: 9
# x with 2 decimals
DecimalX: {=x $_=sprintf("%.2f",$_) =}
TenX: {=x $_=$_*10 =}
RandomVal: {=1 $_=rand() =}
it can be used like this:
myprog() { echo Using "$@"; cat "$@"; }
export -f myprog
parallel --cleanup --header : --tmpl my.tmpl={#}.t myprog {#}.t \
::: x 1.234 2.345 3.45678 ::: y 1 2 3
=item B<--tty>

View file

@ -2862,10 +2862,8 @@ Distributed Resource Management Application API to make jobs run with
different cluster software.
=head3 Future support in GNU Parallel
B<Future> versions of GNU B<parallel> may support templates
with replacement strings. Such as:
GNU B<parallel> B<--tmpl> supports templates with replacement
strings. Such as:
Xval: {x}
Yval: {y}
@ -2873,21 +2871,17 @@ with replacement strings. Such as:
# x with 2 decimals
DecimalX: {=x $_=sprintf("%.2f",$_) =}
TenX: {=x $_=$_*10 =}
RandomVal: {= $_=rand() =}
RandomVal: {=1 $_=rand() =}
that can be used like:
parallel --header : --tmpl my.tmpl={#}.t myprog {#}.t \
::: x 1 2 3 ::: y 1 2 3
Filtering may also be supported as:
Filtering is supported as:
parallel --filter '{1} > {2}' echo ::: 1 2 3 ::: 1 2 3
which will basically do:
parallel echo '{= $arg[1] > $arg[2] and skip() =}' ::: 1 2 3 ::: 1 2 3
https://github.com/eviatarbach/parasweep (Last checked: 2021-01)
@ -2936,6 +2930,28 @@ https://reposhub.com/python/command-line-tools/Akianonymus-parallel-bash.html
(Last checked: 2021-02)
=head2 DIFFERENCES BETWEEN bash-concurrent AND GNU Parallel
B<bash-concurrent> is more an alternative to B<make> than to GNU
B<parallel>. Its input is very similar to a Makefile, where jobs
depend on other jobs.
It has a nice progress indicator where you can see which jobs
completed successfully, which jobs are currently running, which jobs
failed, and which jobs were skipped due to a depending job failed.
The indicator does not deal well with resizing the window.
Output is cached in tempfiles on disk, but is only shown if there is
an error, so it is not meant to be part of a UNIX pipeline. If
B<bash-concurrent> crashes these tempfiles are not removed.
It uses an O(n*n) algorithm, so if you have 1000 independent jobs it
takes 22 seconds to start it.
https://github.com/themattrix/bash-concurrent
(Last checked: 2021-02)
=head2 Todo
https://github.com/Nukesor/pueue

View file

@ -69,12 +69,12 @@ EOF
cat <<'EOF' > "$tmp2"
2: Job:{#} Slot:{%} All:{} Arg[1]:{1} Arg[-1]:{-1} Perl({}+4):{=$_+=4=}
EOF
parallel -j2 --cleanup --tmpl $tmp1=t1.{#} --tmpl $tmp2=t2.{%} \
'cat t1.{#} t2.{%}' ::: 1 2 ::: a b
parallel --colsep , -j2 --cleanup --tmpl $tmp1=t1.{#} --tmpl $tmp2=t2.{%} \
'sleep 0.{#}; cat t1.{#} t2.{%}' ::: 1,a 1,b 2,a 2,b
echo should give no files
ls t[12].*
parallel --cleanup --colsep , -j2 --tmpl $tmp1=t1.{#} --tmpl $tmp2=t2.{%} \
'cat t1.{#} t2.{%}' ::: 1,a 1,b 2,a 2,b
parallel -j2 --cleanup --tmpl $tmp1=t1.{#} --tmpl $tmp2=t2.{%} \
'sleep 0.{#}; cat t1.{#} t2.{%}' ::: 1 2 ::: a b
echo should give no files
ls t[12].*
}

View file

@ -282,6 +282,10 @@ par_open_files_blocks 9 of 21
par_open_files_blocks 10 of 21
par_open_files_blocks 11 of 21
par_open_files_blocks 12 of 21
par_open_files_blocks parallel: Warning: Try running 'parallel -j0 -N 100 --pipe parallel -j0'
par_open_files_blocks parallel: Warning: or increasing 'ulimit -n' (try: ulimit -n `ulimit -Hn`)
par_open_files_blocks parallel: Warning: or increasing 'nofile' in /etc/security/limits.conf
par_open_files_blocks parallel: Warning: or increasing /proc/sys/fs/file-max
par_open_files_blocks 13 of 21
par_open_files_blocks 14 of 21
par_open_files_blocks 15 of 21
@ -479,21 +483,21 @@ par_plus_slot_replacement Seq: 097 97
par_plus_slot_replacement Seq: 098 98
par_plus_slot_replacement Seq: 099 99
par_plus_slot_replacement Seq: 100 100
par_plus_slot_replacement Slot: 1 1
par_plus_slot_replacement Slot: 01 1
par_plus_slot_replacement Slot: 02 2
par_plus_slot_replacement Slot: 03 3
par_plus_slot_replacement Slot: 04 4
par_plus_slot_replacement Slot: 05 5
par_plus_slot_replacement Slot: 06 6
par_plus_slot_replacement Slot: 07 7
par_plus_slot_replacement Slot: 08 8
par_plus_slot_replacement Slot: 09 9
par_plus_slot_replacement Slot: 10 10
par_plus_slot_replacement Slot: 11 11
par_plus_slot_replacement Slot: 12 12
par_plus_slot_replacement Slot: 13 13
par_plus_slot_replacement Slot: 14 14
par_plus_slot_replacement Slot: 15 15
par_plus_slot_replacement Slot: 2 2
par_plus_slot_replacement Slot: 3 3
par_plus_slot_replacement Slot: 4 4
par_plus_slot_replacement Slot: 5 5
par_plus_slot_replacement Slot: 6 6
par_plus_slot_replacement Slot: 7 7
par_plus_slot_replacement Slot: 8 8
par_plus_slot_replacement Slot: 9 9
par_profiles_with_space ### bug #42902: profiles containing arguments with space
par_profiles_with_space /bin/bash=/bin/bash
par_profiles_with_space echo '/bin/bash=/bin/bash'