




























































































































































































































































































    
        
            
                                ($opts->{kff} - 1) . "], " .
                            "\@tmp[" . ($opts->{ksf} + 1) . " .. " .
                            "\@tmp[$opts->{ksf} .. $opts->{kff}])";
                            "substr($tmp2, 0, $opts->{kfc}))";
                            "substr($tmp2, 0, $opts->{kfc}))";
                            ($opts->{kfc} - $opts->{ksc}) . ')';
                        # get filehandle and restart array with it
                        $n .= "," . (defined $5 ? ($4 + 1) . ".$5" : $4);
                        $n .= $6 if $6;
                        $opts->{kst} !~ /b/ && $opts->{kft} !~ /b/) {
                        (!$opts->{kfc} || $opts->{kfc} == 0)) {
                        @fh = (_merge_files($opts, \@fh, [], _get_temp()));
                        @fil = "\$tmp[$opts->{ksf}]";
                        @fil = "join('', substr($tmp1, $opts->{ksc}), " .
                        @fil = "join('', substr($tmp1, $opts->{ksc}), " .
                        @fil = "join(''," .
                        @fil = "substr($tmp1, $opts->{ksc})";
                        @fil = "substr($tmp1, $opts->{ksc}, ". 
                        _debug("\nCreating temp files ...\n") if $opts->{D};
                        if $opts->{D};
                        map &map1, ($rec, $last);
                    "(\$tmp[0] =~ /(\\S.*)/)[0]" : "\$tmp[0]";
                    "\n    )[-1],\n  ";
                    "split //,\n$fil[0]";
                    # and neither has -b, alrighty
                    # do a merge now if at file limit
                    # fine, have it your way!  hurt me!  love me!
                    # getting out of hand now
                    # hmmmmm
                    # if only one field away
                    # if spans two fields, but chars are both 0
                    # reset record count and record array
                    # save to temp file, add new fh to array
                    # simpler if chars are both 0, wicked pissah
                    $n .= $3 if $3;
                    $n .= '.' . ($2 + 1) if defined $2;
                    $n = $1 + 1;
                    $tmp1 = "($tmp1 =~ /(\\S.*)/)[0]";
                    $tmp2 = "($tmp2 =~ /(\\S.*)/)[0]";
                    ($count, @recs) = (0);
                    ($opts->{kff} ? "\$tmp[$opts->{kff}]" : ''));
                    @foo = map {$_->[0]} sort sortsub
                    @foo = sort sort1 ($rec, $last);
                    @recs = map {$_->[0]} sort sortsub map &map1, @recs;
                    @recs = sort sort1 @recs;
                    _debug("$count records reached in `$filein'\n")
                    if ($opts->{kfc} == 0 && $opts->{ksc} == 0 &&
                    if ($opts->{ksc} == 0 &&
                    if (@fh >= $opts->{F}) {
                    if (defined($4)) {
                    join(",\n", map {s/^/      /mg; $_} @fil),
                    local $^W;
                    local $^W;
                    local $^W;
                    local $^W;
                    map &map2, keys %fh);
                    or die "Can't open `$filein' for reading: $!";
                    or die "Can't open `$filein' for reading: $!";
                    push @{$args[0]->{'k'}}, $n;
                    push(@fh, _write_temp(\@recs, $opts));
                    }
                    }
                    }
                    }
                    } else {
                    } else {
                    } elsif (!$opts->{kfc}) {
                    } elsif (($opts->{kff} - $opts->{ksf}) == 1) {
                   (?:\s+\-(\d+)(?:\.(\d+))?([bdfinr]+)?)?$/x) {
                # simpler if one field, goody for us
                # skip leading spaces
                # try again, shall we?
                $aa, $cmp, $bb;
                $args[0]->{'k'} = [$args[0]->{'k'}];
                $args[0]->{'k'} = [];
                $count++;  # keep track of number of records
                $fil[0] = "join '', grep {POSIX::isprint \$_} " .
                $fil[0] = "uc($fil[0])";
                $pos = [$pos];
                $topts->{DD}++;
                $topts->{k}[0] eq 'K' ? $k : "split(/$topts->{t}/, $k)";
                $topts->{r} ? qw($b cmp $a) : qw($a cmp $b);
                (!$uniq || _are_uniq($opts->{K}, $uniq, $fh{$first}));
                ($first) = (map {$_->[0]} sort sortsub
                ($first) = (sort sort2 keys %fh);
                @fil = $opts->{kst} =~ /b/ ?
                _check_last(\@recs);
                _debug("\Sorting leftover records ...\n") if $opts->{D};
                if (   /^\+(\d+)(?:\.(\d+))?([bdfinr]+)?
                if (! defined $opts->{kff} || $opts->{ksf} == $opts->{kff}) {
                if ($count >= $opts->{'y'}) {    # don't go over record limit
                if ($opts->{K}) {
                if ($opts->{K}) {
                if ($opts->{kft} =~ /b/) {
                if ($opts->{kst} =~ /b/) {
                local $^W;
                local $^W;
                my $n;
                my @foo;
                my($tmp1, $tmp2) = ("\$tmp[$opts->{ksf}]",
                open(F, $filein)
                or die "Can't open `$filein' for reading: $!";
                or die "Can't open `$opts->{I}[0]' for reading: $!";
                or die "Can't open `$opts->{I}[0]' for reading: $!";
                push @fil, "\$tmp =~ s/[^\\w\\s]+//g", '"$tmp"';
                push @mapsub, "  " . $fil[0] . ",\n  ";
                push @mapsub, "  (\n" .
                push(@recs, $rec);
                require POSIX;
                return 0 if $foo[0] ne $last || $foo[1] ne $rec;
                return 0 unless _are_uniq($opts->{K}, $last, $rec);
                sysopen(F, $filein, O_RDONLY)
                }
                }
                }
                }
                }
                }
                }
                } else {
                } else {
                } else {
            # $first is arbitrary number assigned to first fh in sort
            # add finished expressions to arrays
            # defaults for main sort sub components
            # do numeric sort
            # do straight compare if all else is equal
            # fail if -u and keys are not unique (assume sorted)
            # fail if records not in proper sort order
            # fold to upper case
            # just open files and get array of handles
            # only alphanumerics and whitespace, override -i
            # only printable characters
            # records leftover, didn't reach record limit
            # reverse sense
            # save value of last record
            # skip stuff if special K
            $cmp = '<=>' if ($opts->{kst} =~ /n/);
            $fh{$first} = $rec;
            $fil[0] = "\$tmp = $fil[0]" if $opts->{kst} =~ /d/;
            $last = $rec;
            $maps{$m} .= "  my \$tmp;\n" if $topts->{DD};
            $maps{$m} .= ",\n  " . join('', @mapsub) if @mapsub;
            $maps{$m} .= "\n  [\$_, $k";
            $maps{$m} .= "]\n}\n";
            $maps{$m} = sprintf "sub {\n  my \@tmp = %s;\n",
            $opts = $k eq 'K' ? $topts : _parse_keydef($k, $topts);
            $opts{kft} .= $_ if $topts->{$_};
            $opts{kft} .= $_ if ($opts{kst} =~ /$_/ || $opts{kft} =~ /$_/);
            $opts{kst} .= $_ if $topts->{$_};
            $opts{kst} .= $_ if ($opts{kst} =~ /$_/ || $opts{kft} =~ /$_/);
            $topts->{K} = 0;
            $topts->{kst} .= $_ if $topts->{$_};
            $topts->{k} = ['K'];    # special K ;-)
            $uniq = $fh{$first};
            '\s+';
            ($bb, $aa) = ($aa, $bb) if ($opts->{kst} =~ /r/);
            ($first) = keys %fh;
            *map1  = eval $maps{map1};
            *map2  = eval $maps{map2};
            *sort1  = eval $sort1;
            *sort2  = eval $sort2;
            *sortsub = eval $sortsub;
            @recs = ();
            _debug("Sorting file $filein ...\n") if $opts->{D};
            close(F);
            defined $topts->{X} ? $topts->{X} :
            defined $topts->{t} ? quotemeta($topts->{t}) :
            delete $fh{$first};
            delete $fh{$first};
            die "Can't create sort sub: $@" if $@;
            die "Can't create sort sub: $@" if $@;
            die "Can't create sort sub: $@" if $@;
            die "Can't create sort sub: $@" if $@;
            die "Can't create sort sub: $@" if $@;
            for (@$pos) {
            if (!exists($args[0]->{'k'})) {
            if (!ref($pos)) {
            if ($filein eq '-') {
            if ($k ne 'K') {
            if ($last) {
            if ($opts->{K}) {
            if ($opts->{kst} =~ /d/) {
            if ($opts->{kst} =~ /f/) {
            if ($opts->{u} && $last) {
            if (@fil > 1) {
            if (@recs) {
            last;
            local $^W;
            local $^W;
            local *F;
            my $count = 0;
            my $curr = $oth{$first};
            my $k = $maps{$m};
            my $n = @sortsub + 2;
            my $pos = $args[0]->{'pos'};
            my $sym = gensym();
            my @argv;
            my @left = $first eq 'X' ? @$recs : <$curr>;
            my($cmp, $ab_, $fab_, $aa, $bb) = qw(cmp $_ $fh{$_} $a $b);
            my($opts, @fil) = ($topts);
            open(F, $opts->{I}[0])
            or die "Can't open `$file' for writing: $!";
            print $fh{$first} if
            print $fh{$first}, @left;
            print $fh{$first};
            push @sortsub, sprintf "%s->[$n] %s %s->[$n]",
            push @sortsub, sprintf "%s->[1] %s %s->[1]",
            push(@fh, $sym);
            sysopen($sym, $filein, O_RDONLY)
            sysopen(F, $opts->{I}[0], O_RDONLY)
            while (defined(my $rec = <F>)) {
            }
            }
            }
            }
            }
            }
            }
            }
            }
            }
            }
            }
            }
            } else {
            } else {
            } else {
            } else {
            } elsif (!ref($args[0]->{'k'})) {
            } elsif ($opts->{kst} =~ /i/) {
        # add finished expression to array
        # defaults for main sort sub components
        # do numeric sort
        # don't bother sorting keys if only one key remains!
        # don't print if -u and not unique
        # fix pos to look like k
        # get current filehandle
        # get text separator or use whitespace
        # if not -u
        # more complex stuff, act like we had -k defined
        # once for each input file
        # reverse sense
        # success, yay
        # use @$recs, not filehandles, if key is X
        $cmp = '<=>' if $topts->{n};
        $file = $tfh;
        $file = \*STDOUT;
        $opts{$_}-- if $opts{$_};
        $sortsub = "sub {\n  " . join(" || \n  ", @sortsub) . "\n}\n";
        $topts->{kst} = '';
        $topts->{t} =
        $topts->{t} =~ s|/|\\/|g if defined $topts->{X};
        $u .= $_;
        %$topts,                            # get other options
        ($_ => scalar <$fh>);
        ($a, $b) = @_;
        ($a, $b) = map &map1, @_;
        ($bb, $aa, $fb, $fa) = ($aa, $bb, $fa, $fb) if $topts->{r};
        (?:,(\d+)(?:\.(\d+))?([bdfinr]+)?)?$/x;
        I => ['file1', 'file2']
        _debug("$sort1\n$sort2\n") if $topts->{D};
        _debug("$sortsub\n$maps{map1}\n$maps{map2}\n") if $topts->{D};
        _debug("No keydef set\n") if $topts->{D};
        _sort_file(@args);
        _sort_file({I=>$args[0], o=>$args[1]});
        for my $m (keys %maps) {
        foreach (qw(b d f i n r)) {
        foreach (qw(b d f i n r)) {
        foreach (qw(d f i n r)) {
        foreach my $filein (@{$opts->{I}}) {
        foreach my $filein (@{$opts->{I}}) {
        foreach my $k (@{$topts->{k}}) {
        if (! $topts->{u} ) {
        if (!$opts->{u} && keys %fh == 1) {
        if ($opts->{I}[0] eq '-') {
        if ($opts->{u}) {
        if ($topts->{kst} =~ /[bdfi]/) {
        if (defined $rec) {     # bring up next record for this filehandle
        if (exists($args[0]->{'pos'})) {
        kfc => (defined($5) ? $5 : undef),  # end field char end
        kff => (defined($4) ? $4 : undef),  # end field
        kft => $6 || '',                    # end field type
        ksc => $2 || 0,                     # start field char start
        ksf => $1 || 0,                     # start field
        kst => $3 || '',                    # start field type
        last if m/^=/;
        last if m/^=head1 SYNOPSIS$/;
        local $^W;
        local $^W;
        local *F;
        my $curr = $oth{$first};
        my $fh = $oth{$_};
        my $last;
        my $rec = $first eq 'X' ? shift @$recs : scalar <$curr>;
        my $sort1 = "sub { $aa $cmp $bb }\n";
        my $sort2 = "sub { $fa $cmp $fb }\n";
        my $tfh = gensym();
        my($cmp, $aa, $bb, $fa, $fb) = qw(cmp $a $b $fh{$a} $fh{$b});
        my(%maps, $sortsub, $mapsub) = (map1 => '$_', map2 => '$fh{$_}');
        o => 'outfile', I => ['file1', 'file2']
        print $temp map {$_->[0]} sort sortsub map &map1, @{$recs};
        print $temp sort sort1 @{$recs};
        r => 1, k => '2.2,2.2', o => 'outfile',
        return &sort1;
        return &sortsub;
        return 1;
        sysopen($tfh, $file, O_WRONLY|O_CREAT|O_EXCL)
        u => 1, r => 1, k => ['5.3,5.5rn', '2.2,2.2'],
        while (defined(my $rec = <F>)) {
        {
        {
        {
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        }
        } else {
        } else {
        } else {                # we don't need you anymore
    # "K" == "no k", for later
    # add new record separator if not one there
    # arbitrarily named keys, store handles as values
    # do the merge thang, uh huh, do the merge thang
    # except for b, flags on one apply to the other
    # extra records, special X "handle"
    # file and get a reference to it
    # get input files into anon array if not already
    # gurgle
    # if merging sorted files
    # if no keydefs set
    # if no keydefs set
    # if nothing in kst or kft, use other flags possibly passed
    # if output file is a path, not a reference to a file, open
    # match handle key in %oth to next record of the handle    
    # only check to see if file is sorted
    # ooo, get ready, get ready
    # output to STDOUT if no output file provided
    # record separator, default to \n
    # see big ol' mess below
    # set defaults at zero or undef
    # set output and other defaults
    # their idea of 1 is not ours
    # we need the options, filehandles, and output file
    $fh{X} = shift @$recs if @$recs;
    $k =~ /^(\d+)(?:\.(\d+))?([bdfinr]+)?
    $opts->{'y'} ||= $ENV{MAX_SORT_RECORDS} || 200000;  # default max records
    $opts->{F}   ||= $ENV{MAX_SORT_FILES}   || 40;      # default max files
    $opts->{I} = [$opts->{I}] unless ref $opts->{I};
    $opts->{K} = $opts->{k} ? 0 : 1;
    $opts->{k} = $opts->{k} ? [$opts->{k}] : [] if !ref($opts->{k});
    $opts->{o}   = !$opts->{o} ? '' : $opts->{o};
    $u =~ s/\n//;
    ${$_[0]}[-1] .= $/ if (${$_[0]}[-1] !~ m|$/$|);
    $| = 0; # just in case, use the buffer, you knob
    %fh  = map {
    %oth = map {($o++ => $_)} @$fh;
    );
    +field_start[.first_char][type] [-field_end[.last_char][type]]
    I => [qw(file_1 file_2)],
    IO::File->new_tmpfile;
    _check_last($recs);
    _debug("New tempfile: $temp\n") if $opts->{D};
    _debug("\nCreating sorted $file ...\n") if $opts->{D};
    _debug("\nDone!\n\n") if $opts->{D};
    _make_sort_sub($opts);
    close($close) unless $$close eq 'main::STDOUT'; # don't close STDOUT
    die "Usage:$u";
    field_start[.first_char][type][,field_end[.last_char][type]]
    for (qw(ksf ksc kff)) { #  kfc stays same
    if (!$opts{kst} && !$opts{kft}) {
    if ($file eq '') {
    if ($nok) {
    if ($opts->{K}) {
    if ($opts->{c}) {
    if ($topts->{K}) {
    if ($topts->{K}) {
    if (ref($args[0])) {
    local $/ = "\n";    # in case changed
    local $/ = $opts->{R} ? $opts->{R} : "\n";
    local $\;   # don't mess up our prints
    local $^W;
    my $close = _merge_files($opts, \@fh, \@recs, $opts->{o});
    my $nok = shift;
    my $oldfh = select($file);
    my $temp = _get_temp() or die "Can't get temp file: $!";
    my $u;
    my %opts = (
    my @args = @_;
    my($k, $topts) = @_;
    my($opts, $fh, $recs, $file) = @_;
    my($opts, @fh, @recs) = shift;
    my($recs, $opts) = @_;
    my($topts, @sortsub, @mapsub, @sort1, @sort2) = shift;
    my($uniq, $first, $o, %oth);
    o => 'file_new', k => '5.3,5.5rn', -t => '|'
    pos => '+1 -2'              ->  k => '2,2'
    pos => '+1.1 -1.2'          ->  k => '2.2,2.2'
    pos => '+2.0 -3.0'          ->  k => '3.1,4.0'
    pos => '+2.1 -2.4'          ->  k => '3.2,3.4'
    pos => ['+1 -2', '+3 -5']   ->  k => ['2,2', '4,5']
    pos => ['+2', '+0b -1']     ->  k => ['3', '1b,1']
    print STDERR @_;
    require IO::File;
    return $file;
    return $temp;
    return 1;   # yay
    return \%opts;
    seek DATA, 0, 0;
    seek($file, 0, 0);  # might need to read back from it
    seek($temp, 0, 0);  # might need to read back from it
    select($oldfh);
    sort_file('file');
    sort_file({
    sort_file({
    sort_file({c => 1, t => ':', k => '3n', I => '/etc/passwd'});
    sort_file({k => 2, I => 'file'});
    sort_file({t => ':', k => '3n', I => '/etc/passwd'});
    usage() unless @{$opts->{I}};
    use File::Sort qw(sort_file);
    while (<DATA>) {
    while (<DATA>) {
    while (keys %fh) {
    }
    }
    }
    }
    }
    }
    }
    }
    }
    }
    }
    }
    } else {
    } else {
    } else {
    } else {
    } else {
    } else {
    } elsif (! ref($file)) {
    } elsif ($opts->{'m'}) {
    } keys %oth;
    });
    });
  OPTION => VALUE
  OPTION => [VALUE1, VALUE2]
  sort_file('file1', 'file1.sorted');
  sort_file({
  use File::Sort qw(sort_file);
  });
# plus optional arrayref of sorted scalars
# take optional arrayref of handles of sorted files,
$VERSION = '0.80';
***DANGER, WILL ROBINSON***
=back
=back
=back
=back
=back
=cut
=head1 AUTHOR
=head1 DESCRIPTION
=head1 ENVIRONMENT
=head1 EXAMPLES
=head1 EXPORT
=head1 HISTORY
=head1 NAME
=head1 SEE ALSO
=head1 SYNOPSIS
=head1 THANKS
=head1 TODO
=head1 VERSION
=head2 Not Implemented
=head2 Options
=item Better debugging and error reporting
=item C<D>
=item C<F> I<MAX_SORT_FILES>
=item C<R> I<STRING>
=item C<X> I<STRING>
=item C<b>
=item C<c>
=item C<d>
=item C<f>
=item C<i>
=item C<k> I<pos1[,pos2]>
=item C<m>
=item C<n>
=item C<o> I<OUTPUT>
=item C<pos> I<+pos1 [-pos2]>
=item C<r>
=item C<t> I<STRING>
=item C<u>
=item C<y> I<MAX_SORT_RECORDS>
=item Do bytes instead of lines
=item LC_COLLATE
=item LC_CTYPE
=item MAX_SORT_FILES
=item MAX_SORT_RECORDS
=item Performance hit with -u
=item Whoops, fix input via STDIN
=item v0.01 (18 December 1997)
=item v0.02 (19 December 1997)
=item v0.03 (23 December 1997)
=item v0.10 (03 January 1998)
=item v0.11 (04 January 1998)
=item v0.16 (24 December 1998)
=item v0.17 (30 December 1998)
=item v0.18 (31 January 1998)
=item v0.20
=item v0.90, Friday, April 30, 1999
=over 4
=over 4
=over 4
=over 4
=over 4
@EXPORT = ();
@EXPORT_OK = qw(sort_file);
@ISA = qw(Exporter);
Added c option to check sorting.
Added reverse and numeric sorting options.
Added unique and merge-only options.
Albert Dvornik E<lt>bert@mit.eduE<gt>,
Also now use C<IO::File> to create temp files, so the TMPDIR option is
Andrew M. Langmead E<lt>aml@world.std.comE<gt>,
B<b> option, but applies only to the field_start or field_end to which
B<b>, B<d>, B<f>, B<i>, B<n>, B<r>.  The b modifier behaves like the
B<d> overrides B<i>.
Brian L. Matthews E<lt>blm@halcyon.comE<gt>,
C<IO::File> object.
Check that single input fle is ordered as specified by the arguments and
Chris Nandor E<lt>pudge@pobox.comE<gt>, http://pudge.net/
Complete rewrite.  Took the code from this module to write sort
Consider all lower-case characters that have upper-case equivalents,
Copyright (c) 1999 Chris Nandor.  All rights reserved.  This program is
Default is 200,000.  Maximum number of records to use before writing
Default is 200,000. This may eventually change to be kbytes instead of
Determine the locale for ordering rules.
Determine the locale for the interpretation of sequences of bytes of
Does numeric instead of string compare, using whatever perl considers to
E<lt>charE<gt>E<lt>charE<gt> delimits an empty field).  If B<t> is not
Except when the B<u> option is specified, lines that otherwise compare
Exports C<sort_file> on request.
File::Sort - Sort a file or merge sort multiple files
First release.
Fixed bug in C<_merge_files> that tried to C<open> a passed
Fixed bug with unique option (didn't work :).
Fixed up docs and did some more tests and benchmarks.
For the anal sysadmin, check that passwd(4) file is sorted by numeric
Gene Hsu E<lt>gene@moreinfo.comE<gt>,
Gurusamy Sarathy E<lt>gsar@activestate.comE<gt>.
Here are some equivalencies:
If any modifier is attached to a field_start or a field_end, no option
If no B<k> option is specified, a default sort key of the entire line
If the options are not listed as implemented above, or are not
If used with the B<c> option check that there are no lines with
If you need the old interface, the old module will remain on CPAN, but
Ignore leading blank characters when determining the starting and ending
Ignores all characters that are non-printable, according to the current
It is best if you Don't Do That.  Pick one and stick with it.
MAX_SORT_RECORDS environment variable.
Made CHUNK default a lot larger, which improves performance.  On
Matthias Neeracher E<lt>neeri@iis.ee.ethz.chE<gt>,
Maximum number of lines (records) read before writing to temp file.
Maximum number of open temp files to use before merging open temp
Maximum number of temp files to be held open at once.  Default to 40,
Merge only; the input files are assumed to already be sorted.
Mike Blazer E<lt>blazer@mail.nevalink.ruE<gt>,
Miko O'Sullivan E<lt>miko@idocs.comE<gt>,
Mixing B<+pos1> B<pos2> with B<k> is allowed, but will result in all of
More cleanup; fixed special case of no linebreak on last line; wrote test 
Occurrences of the B<k> option are significant in command line order. 
One year between releases was too long.  I made changes Miko O'Sullivan
Otherwise, the B<b> option can be attached indepently to each
Print passwd(4) file sorted by numeric user ID.
Print to STDOUT if no output file supplied.
Record separator, defaults to newline.
Reverse the sense of the comparisons.
Rich Morin E<lt>rdm@cfcl.comE<gt>,
Same as B<t>, but I<STRING> is interpreted as a Perl regular expression
Same sort but sorting numerically on characters 3 through 5 of
See L<"HISTORY">.
Send debugging information to STDERR.  Behavior subject to change.
Similar to B<k>, these are mostly obsolete switches, but some people
Some cleanup; made it not subject to system file limitations; separated 
Sort contents of file by second key in file.
Sort file by straight string compare of each line, sending
Sort, in reverse order, contents of file1 and file2, placing
Specify that only blank characters and alphanumeric characters,
Specify the name of an I<OUTPUT> file to be used instead of the standard
Switched to sysopen for better portability.
Tests 3 and 4 failed because we hit the open file limit in the
The following options are available, and are passed in the hash
The following options override the default ordering rules. When ordering
The good news is that it should not be too difficult to update your
The interface has changed in some significant ways.
The keydef argument is a restricted sort key field definition. The
The string matched by I<STRING> is not included in the fields
This includes B<T> and B<z>.
This interface will always be supported, though a more perlish
This module sorts text files by lines (or records).  Comparisons
Tom Christiansen E<lt>tchrist@perl.comE<gt>,
Tom Phoneix E<lt>rootbeer@teleport.comE<gt>,
Unique: Suppresses all but one in each set of lines having equal keys.
Use I<STRING> as the field separator character; char is not considered
Vicki Brown E<lt>vlb@cfcl.comE<gt>,
Where an option can take multiple values (like C<I>, C<k>, and C<pos>),
Where field_end in B<k> specified the last position to be included,
Where the OPTION is a switch, it should be passed a boolean VALUE
__END__
according to the current locale setting, are significant in comparisons.
according to the current locale setting, to be the upper-case equivalent
and are performed lexicographically. By default, if keys are not given,
applies to either.
are based on one or more sort keys extracted from each line of input,
are counted from 0 instead of 1.  B<pos2> must immediately follow
are used for options, but there are also some key behavioral differences.
as older Windows ports had quite a small limit.  Can also specify
as the sort key.
at all if MAX_SORT_RECORDS is never reached.
be a number in numeric comparisons.
before the first B<k> option, it is applied to all B<k> options. 
character classification for the B<b>, B<d>, B<f>, B<i> and B<n>
character is a field separator.
characters in arguments and input files) and the behaviour of
code to use the new interface.
comparison.  The order in which lines that still compare equal are
consecutive lines with duplicate keys, in addition to checking that the
corresponding B<+pos1>.  The rest should be the same as the B<k> option.
equal are ordered as if none of the options B<d>, B<f>, B<i>, B<n>
escaped internally, and will be escaped for you).
faster, while supporting more options for sorting, including delimited
field ordering rules are applied globally to all sort keys. When attached
field).  See L<perlre> and L<perlfunc/split>.
field_start or field_end option argument (see below).
files), changed docs.  (Mike Blazer, Gurusamy Sarathy)
files.  Overriden by B<F> option.
for the purposes of comparison.
for total number of temp files from 50 to 40 (leave room for other open
format of this definition is:
free software; you can redistribute it and/or modify it under the terms
global ordering options for that key.
input file is sorted.
instead.  Do not escape any characters (C</> characters need to be
interface may be offered in the future, as well.  This interface
is basically a mapping of the command-line options to the Unix
is used.  When there are multiple keys fields, later keys are compared
it is attached. The other modifiers behave like the corresponding
it specifes the last position to NOT be included.  Also, numbers
like them and want to use them.  Usage is:
lines.  Lines was easier to implement.  Can also specify with
listed in TODO below, they are not in the plan for implementation.
locale setting.
low-memory systems, or where (e.g.) the MacPerl binary is not allocated
many parts out into separate functions.
maximal non-empty sequence of blank characters that follows a non-blank
much RAM, it might need to be lowered.
no longer supported.  Hopefully made the whole thing more robust and
occurrence of char is significant (for example,
of 1 or 0.
of the Artistic License, distributed with Perl.
only after all earlier keys compare equal.
only the exit code is affected.
options appear independent of any key field specifications, the requested
options, but apply only to the key field to which they are attached;
options.
or B<k> were present (but with B<r> still in effect, if it was
output in outfile and using second character of second field
output to STDOUT.
output.
package File::Sort;
portion of the line, and type is a modifier from the list of characters
positions of a restricted sort key.  If the B<b> option is specified
reference passed to the function in the format:
regexes in parentheses will add that matched expression as an extra
require Exporter;
sort regards each input line as a single field.  The sort is a merge
sort utility.
sort(1), locale, PPT project, <URL:http://language.perl.com/ppt/>.
sort.  If you don't like that, feel free to change it.
sorts, and arbitrary sorts.
specified) and with all bytes in the lines significant to the
specified, blank characters are used as default field separators; each
standard Windows port of perl5.004_02 (50).  Adjusted the default
sub _are_uniq {
sub _check_last {
sub _debug {
sub _get_temp { # nice and simple
sub _make_sort_sub {
sub _merge_files {
sub _parse_keydef {
sub _sort_file {
sub _write_temp {
sub sort_file {
sub usage {
suite; fixed warning for redefined subs (sort1 and sort2).
text data as characters (for example, single- versus multi-byte
the B<+pos1> B<pos2> options being ordered AFTER the B<k> options.
the collating sequence of the current locale.  No output is produced;
the fifth field first, and only return records with unique keys.
the interface has changed slightly, mostly in regard to what letters
themselves, unless demanded by perl's regex and split semantics (e.g.,
they have this effect if specified with field_start, field_end, or both.
to a specific key (see B<k>), the specified ordering options override all
to a temp file.  Overriden by B<y> option.
to be part of a field (although it can be included in a sort key).  Each
use Carp;
use Fcntl qw(O_RDONLY O_WRONLY O_EXCL O_CREAT);
use Symbol qw(gensym);
use locale;
use strict;
use vars qw($VERSION *sortsub *sort1 *sort2 *map1 *map2 %fh);
use vars qw(@ISA @EXPORT @EXPORT_OK);
user ID.
utility for PPT project, then brought changes back over.  As a result
v0.80, Friday, April 30, 1999
values may be passed via an anonymous array:
wanted, and I didn't even know I had made them.
where field_start and field_end define a key field restricted to a
will not be supported.  Sorry for any inconvenience this may cause.
with MAX_SORT_FILES environment variable.  No temp files will be used
written is unspecified.
}
}
}
}
}
}
}
}
}
}
}
