parallel: Bug fix: If replace string contains regexp special char it should be escaped.

Most xargs options implemented with unittest - though still undocumented
This commit is contained in:
Ole Tange 2010-02-04 00:54:06 +01:00
parent f5cca23204
commit 0214645ed9
5 changed files with 319 additions and 36 deletions

View file

@ -133,7 +133,8 @@ output from different commands to be mixed. Can be reversed with B<-g>.
=item B<-v>
Verbose. Print the job to be run on STDOUT. Can be reversed with B<-s>.
Verbose. Print the job to be run on STDOUT. Can be reversed with
B<--silent>.
=item B<--xargs>
=item B<-m>
@ -512,12 +513,12 @@ parallel --wait /tmp/comfile will wait until no more locks on the file
Copyright (C) 2007-10-18 Ole Tange, http://ole.tange.dk
Copyright (C) 2008-2009 Ole Tange, http://ole.tange.dk
Copyright (C) 2008-2010 Ole Tange, http://ole.tange.dk
=head1 LICENSE
Copyright (C) 2007-2009 Free Software Foundation, Inc.
Copyright (C) 2007-2010 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@ -535,7 +536,7 @@ along with this program. If not, see <http://www.gnu.org/licenses/>.
=head1 DEPENDENCIES
B<parallel> uses Perl, and the Perl modules Getopt::Std, IPC::Open3,
B<parallel> uses Perl, and the Perl modules Getopt::Long, IPC::Open3,
Symbol, IO::File, POSIX, and File::Temp.
@ -571,36 +572,35 @@ GetOptions("debug|D" => \$::opt_D,
"quote|q" => \$::opt_q,
"I=s" => \$::opt_I,
"jobs|j=s" => \$::opt_P,
# xargs-compatability - implemented - unittest missing
# xargs-compatibility - implemented, man, unittest
"max-procs|P=s" => \$::opt_P,
"delimiter|d=s" => \$::opt_d,
# xargs-compatibility - implemented, unittest - man missing
"max-chars|s=i" => \$::opt_s,
"arg-file|a=s" => \$::opt_a,
"delimiter|d=s" => \$::opt_d,
"no-run-if-empty|r" => \$::opt_r,
## echo " " | parallel -r echo
## echo " " | parallel echo
"replace|i:s" => \$::opt_i,
"E=s" => \$::opt_E,
"eof|e:s" => \$::opt_E,
"max-args|n=i" => \$::opt_n,
## (echo a b;echo c;echo d) | parallel -k -n1 -X echo
## (echo a b;echo c;echo d) | parallel -k -n2 -X echo
"verbose|t" => \$::opt_t,
"help|h" => \$::opt_h,
"version" => \$::opt_version,
## xargs-compatibility - implemented - unittest missing - man missing
"interactive|p" => \$::opt_p,
## How to unittest? tty skal emuleres
"verbose|t" => \$::opt_t,
# xargs-compatability - unimplemented
"help|h" => \$::opt_help,
"L=i" => \$::opt_L,
"max-lines|l:i" => \$::opt_l,
# (echo a b;echo c) | xargs -l1 echo
# (echo a b' ';echo c) | xargs -l1 echo
"version" => \$::opt_version,
## (echo a b;echo c) | xargs -l1 echo
## (echo a b' ';echo c) | xargs -l1 echo
"show-limits" => \$::opt_show_limits,
"exit|x" => \$::opt_x,
) || die_usage();
# Defaults:
$Global::version = 20100203;
$Global::debug = 0;
$Global::processes_to_run = 10;
$command = undef;
@ -627,7 +627,7 @@ if(defined $::opt_u) { $Global::grouped = 0; }
if(defined $::opt_c) { $Global::input_is_filename = 0; }
if(defined $::opt_f) { $Global::input_is_filename = 1; }
if(defined $::opt_0) { $/ = "\0"; }
if(defined $::opt_d) { $/ = $::opt_d; }
if(defined $::opt_d) { my $e="sprintf \"$::opt_d\""; $/ = eval $e; }
if(defined $::opt_p) { $Global::interactive = $::opt_p; }
if(defined $::opt_q) { $Global::quoting = 1; }
if(defined $::opt_r) { $Global::ignore_empty = 1; }
@ -636,8 +636,10 @@ if(defined $::opt_I) { $Global::replacestring = $::opt_I; }
if(defined $::opt_i and $::opt_i) { $Global::replacestring = $::opt_i; }
if(defined $::opt_E and $::opt_E) { $Global::end_of_file_string = $::opt_E; }
if(defined $::opt_n and $::opt_n) { $Global::max_number_of_args = $::opt_n; }
if(defined $::opt_h) { die_usage(); }
if(defined $::opt_version) { version(); exit(0); }
if(defined $::opt_a) {
if(defined $::opt_a) {
if(not open(ARGFILE,"<".$::opt_a)) {
print STDERR "parallel: Cannot open input file `$::opt_a': No such file or directory\n";
exit(-1);
@ -677,18 +679,18 @@ sub generate_command_line {
my ($length_of_command_no_args);
if($Global::xargs or $Global::Xargs) {
# Count number of {}'s on the command line
$number_of_substitution = ($command =~ s/$Global::replacestring/$Global::replacestring/go);
$number_of_substitution = ($command =~ s/\Q$Global::replacestring\E/$Global::replacestring/go);
$number_of_substitution ||= 1;
}
if($Global::xargs) {
my $c = $command;
# remove all {}s
$c =~ s/$Global::replacestring//go;
$c =~ s/\Q$Global::replacestring\E//go;
$length_of_command_no_args = length($c);
}
if($Global::Xargs) {
my $c = $command;
while($c =~ s/(\S*$Global::replacestring\S*)//o) {
while($c =~ s/(\S*\Q$Global::replacestring\E\S*)//o) {
# Length of context minus the {}
$length_of_context += length($1) - 2;
}
@ -713,7 +715,7 @@ sub generate_command_line {
if($quoted_args[0]) {
last;
} else {
die ("Command line too long at $next_arg");
die ("Command line too long at: $next_arg");
}
}
if($Global::max_number_of_args and $number_of_args >= $Global::max_number_of_args) {
@ -723,17 +725,17 @@ sub generate_command_line {
}
if(@quoted_args) {
$job_line = $command;
if(defined $job_line and $job_line =~/$Global::replacestring/o) {
if(defined $job_line and $job_line =~/\Q$Global::replacestring\E/o) {
# substitute {} with args
if($Global::Xargs) {
# Context sensitive replace (foo{}bar with fooargsbar)
while($job_line =~/$Global::replacestring/o) {
$job_line =~ /(\S*$Global::replacestring\S*)/ or die ("This should never happen");
while($job_line =~/\Q$Global::replacestring\E/o) {
$job_line =~ /(\S*\Q$Global::replacestring\E\S*)/ or die ("This should never happen");
my $wordarg = $1;
my @all_word_arg;
for my $arg (@quoted_args) {
my $substituted = $wordarg;
$substituted=~s/$Global::replacestring/$arg/go;
$substituted=~s/\Q$Global::replacestring\E/$arg/go;
push @all_word_arg, $substituted;
}
my $all_word_arg = join(" ",@all_word_arg);
@ -743,7 +745,7 @@ sub generate_command_line {
} else {
# Normal replace {} with args
my $arg=join(" ",@quoted_args);
$job_line =~ s/$Global::replacestring/$arg/go;
$job_line =~ s/\Q$Global::replacestring\E/$arg/go;
}
} else {
# append args
@ -948,11 +950,11 @@ sub user_requested_processes {
my $opt_P = shift;
if(defined $opt_P) {
if($opt_P =~ /^\+(\d+)$/) {
# E.g. -j +2
# E.g. -P +2
my $j = $1;
$processes = $j + no_of_cpus();
} elsif ($opt_P =~ /^-(\d+)$/) {
# E.g. -j -2
# E.g. -P -2
my $j = $1;
$processes = no_of_cpus() - $j;
} elsif ($opt_P =~ /^(\d+)\%$/) {
@ -961,7 +963,7 @@ sub user_requested_processes {
} elsif ($opt_P =~ /^(\d+)$/) {
$processes = $1;
if($processes == 0) {
# -j 0 = infinity (or at least close)
# -P 0 = infinity (or at least close)
$processes = 2**31;
}
} else {
@ -1303,6 +1305,19 @@ sub usage {
print "parallel [-0cdfgkqsuvxX] [-j num] [command [arguments]] < list_of_arguments\n";
}
sub version {
print join("\n",
"parallel $Global::version",
"Copyright (C) 2007-2010 Free Software Foundation, Inc.",
"License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>",
"This is free software: you are free to change and redistribute it.",
"There is NO WARRANTY, to the extent permitted by law.",
"",
"Written by Ole Tange <http://ole.tange.dk>.\n"
);
}
#
# Debugging
#
@ -1371,5 +1386,4 @@ $main::opt_X = $main::opt_x = $main::opt_k = $main::opt_d =
$main::opt_P = $main::opt_i = $main::opt_p = $main::opt_a =
$main::opt_version = $main::opt_L = $main::opt_l =
$main::opt_show_limits = $main::opt_n = $main::opt_e = $main::opt_t =
$main::opt_E = $main::opt_r = $main::opt_help = $Global::xargs =
$Global::keeporder = 0;
$main::opt_E = $main::opt_r = $Global::xargs = $Global::keeporder = 0;

View file

@ -124,7 +124,7 @@
.\" ========================================================================
.\"
.IX Title "PARALLEL 1"
.TH PARALLEL 1 "2010-02-03" "perl v5.10.1" "User Contributed Perl Documentation"
.TH PARALLEL 1 "2010-02-04" "perl v5.10.1" "User Contributed Perl Documentation"
.\" For nroff, turn off justification. Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
@ -221,7 +221,8 @@ Ungroup output. Output is printed as soon as possible. This may cause
output from different commands to be mixed. Can be reversed with \fB\-g\fR.
.IP "\fB\-v\fR" 9
.IX Item "-v"
Verbose. Print the job to be run on \s-1STDOUT\s0. Can be reversed with \fB\-s\fR.
Verbose. Print the job to be run on \s-1STDOUT\s0. Can be reversed with
\&\fB\-\-silent\fR.
.IP "\fB\-\-xargs\fR =item \fB\-m\fR" 9
.IX Item "--xargs =item -m"
Multiple. Insert as many arguments as the command line length permits. If
@ -571,10 +572,10 @@ parallel \-\-wait /tmp/comfile will wait until no more locks on the file
.IX Header "AUTHOR"
Copyright (C) 2007\-10\-18 Ole Tange, http://ole.tange.dk
.PP
Copyright (C) 2008\-2009 Ole Tange, http://ole.tange.dk
Copyright (C) 2008\-2010 Ole Tange, http://ole.tange.dk
.SH "LICENSE"
.IX Header "LICENSE"
Copyright (C) 2007\-2009 Free Software Foundation, Inc.
Copyright (C) 2007\-2010 Free Software Foundation, Inc.
.PP
This program is free software; you can redistribute it and/or modify
it under the terms of the \s-1GNU\s0 General Public License as published by
@ -590,7 +591,7 @@ You should have received a copy of the \s-1GNU\s0 General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
.SH "DEPENDENCIES"
.IX Header "DEPENDENCIES"
\&\fBparallel\fR uses Perl, and the Perl modules Getopt::Std, IPC::Open3,
\&\fBparallel\fR uses Perl, and the Perl modules Getopt::Long, IPC::Open3,
Symbol, IO::File, \s-1POSIX\s0, and File::Temp.
.SH "SEE ALSO"
.IX Header "SEE ALSO"

View file

@ -0,0 +1,100 @@
1
2
3
4
5
6
7
8
9
10
1
2
3
4
5
6
7
8
9
10
replace
replace
replace
replace
replace
replace
replace
include this
include this
include this
include this
include this
include this
line 1
line 2
line 3
line 1 line 1
line 2
line 1
line 2
line 3
line 1 line 1
line 2
line 1
line 2
line 3
line 1
line 2
line 3
line 1 line 1
line 2
line 1 line 1
line 2
1
2
3
4
5
6
7
8
9
10
1
2
3
4
5
6
7
8
9
10
This is line 1
This is line 2
This is line 3
This is line 1
This is line 2
This is line 3
line 1
line 2
line 3
line 1
line 2
line 3
line 1 line 1
line 2
line 1 line 1
line 2
2
2
7
echo bar
echo car
echo far
echo bar
echo car
echo far

View file

@ -0,0 +1,68 @@
#!/bin/bash
# Test xargs compatibility
# Test -a and --arg-file: Read input from file instead of stdin
seq 1 10 >/tmp/$$
parallel -a /tmp/$$ echo
parallel --arg-file /tmp/$$ echo
# Test -i and --replace: Replace with argument
(echo a; echo END; echo b) | parallel -k -i -eEND echo repl{}ce
(echo a; echo END; echo b) | parallel -k --replace -eEND echo repl{}ce
(echo a; echo END; echo b) | parallel -k -i+ -eEND echo repl+ce
(echo a; echo END; echo b) | parallel -k --replace + -eEND echo repl+ce
(echo a; echo END; echo b) | parallel -k --replace== -eEND echo repl=ce
(echo a; echo END; echo b) | parallel -k --replace=^ -eEND echo repl^ce
(echo a; echo END; echo b) | parallel -k -I^ -eEND echo repl^ce
# Test -E: Artificial end-of-file
(echo include this; echo END; echo not this) | parallel -k -E END echo
(echo include this; echo END; echo not this) | parallel -k -EEND echo
# Test -e and --eof: Artificial end-of-file
(echo include this; echo END; echo not this) | parallel -k -e END echo
(echo include this; echo END; echo not this) | parallel -k -eEND echo
(echo include this; echo END; echo not this) | parallel -k --eof=END echo
(echo include this; echo END; echo not this) | parallel -k --eof END echo
# Test -n and --max-args: Max number of args per line (only with -X and -m)
(echo line 1;echo line 2;echo line 3) | parallel -k -n1 -m echo
(echo line 1;echo line 1;echo line 2) | parallel -k -n2 -m echo
(echo line 1;echo line 2;echo line 3) | parallel -k -n1 -X echo
(echo line 1;echo line 1;echo line 2) | parallel -k -n2 -X echo
(echo line 1;echo line 2;echo line 3) | parallel -k --max-args=1 -X echo
(echo line 1;echo line 2;echo line 3) | parallel -k --max-args 1 -X echo
(echo line 1;echo line 1;echo line 2) | parallel -k --max-args=2 -X echo
(echo line 1;echo line 1;echo line 2) | parallel -k --max-args 2 -X echo
# Test --max-procs and -P: Number of processes
seq 1 10 | parallel -k --max-procs +0 echo
seq 1 10 | parallel -k -P 200% echo
# Test --delimiter and -d: Delimiter instead of newline
# Yes there is supposed to be an extra newline for -d N
echo line 1Nline 2Nline 3 | parallel -k -d N echo This is
echo line 1Nline 2Nline 3 | parallel -k --delimiter N echo This is
printf "line 1\0line 2\0line 3" | parallel -d '\0' echo
printf "line 1\tline 2\tline 3" | parallel --delimiter '\t' echo
# Test --max-chars and -s: Max number of chars in a line
(echo line 1;echo line 1;echo line 2) | parallel -k --max-chars 25 -X echo
(echo line 1;echo line 1;echo line 2) | parallel -k -s 25 -X echo
# Test --no-run-if-empty and -r: This should give no output
echo " " | parallel -r echo
echo " " | parallel --no-run-if-empty echo
# Test --help and -h: Help output (just check we get the same amount of lines)
parallel -h | wc -l
parallel --help | wc -l
# Test --version: Version output (just check we get the same amount of lines)
parallel --version | wc -l
# Test --verbose and -t
(echo b; echo c; echo f) | parallel -k -t echo {}ar 2>&1 >/dev/null
(echo b; echo c; echo f) | parallel -k --verbose echo {}ar 2>&1 >/dev/null

View file

@ -0,0 +1,100 @@
1
2
3
4
5
6
7
8
9
10
1
2
3
4
5
6
7
8
9
10
replace
replace
replace
replace
replace
replace
replace
include this
include this
include this
include this
include this
include this
line 1
line 2
line 3
line 1 line 1
line 2
line 1
line 2
line 3
line 1 line 1
line 2
line 1
line 2
line 3
line 1
line 2
line 3
line 1 line 1
line 2
line 1 line 1
line 2
1
2
3
4
5
6
7
8
9
10
1
2
3
4
5
6
7
8
9
10
This is line 1
This is line 2
This is line 3
This is line 1
This is line 2
This is line 3
line 1
line 2
line 3
line 1
line 2
line 3
line 1 line 1
line 2
line 1 line 1
line 2
2
2
7
echo bar
echo car
echo far
echo bar
echo car
echo far