| 1 |
#!/usr/bin/perl -w |
| 2 |
############################################################################## |
| 3 |
# $Id: xmlsort,v 1.1.1.1 2002/06/14 20:40:12 grantm Exp $ |
| 4 |
# |
| 5 |
# Title: xmlsort |
| 6 |
# |
| 7 |
# Author: Grant McLean <[email protected]> |
| 8 |
# |
| 9 |
# Script for sorting 'records' in XML files. Use -h option for help. |
| 10 |
# |
| 11 |
|
| 12 |
use strict; |
| 13 |
|
| 14 |
use Getopt::Long; |
| 15 |
use Pod::Usage; |
| 16 |
|
| 17 |
use IO::File; |
| 18 |
use XML::SAX::ParserFactory; |
| 19 |
use XML::SAX::Writer; |
| 20 |
use XML::Filter::Sort; |
| 21 |
|
| 22 |
|
| 23 |
############################################################################## |
| 24 |
# Handle command line parameters |
| 25 |
# |
| 26 |
|
| 27 |
my %opt = (); |
| 28 |
|
| 29 |
GetOptions(\%opt, 'r=s', 'k=s', 'i', 's', 't=s', 'm=s', 'h') || |
| 30 |
pod2usage(0); |
| 31 |
|
| 32 |
pod2usage({-verbose => 2, -exitval => 0}) if($opt{h}); |
| 33 |
|
| 34 |
pod2usage(0) unless($opt{r}); |
| 35 |
|
| 36 |
my $filename = shift || '-'; |
| 37 |
|
| 38 |
|
| 39 |
############################################################################## |
| 40 |
# Build up the list of options for constructing the sort filter object. |
| 41 |
# |
| 42 |
|
| 43 |
my %sort_opts = ( Record => $opt{r} ); |
| 44 |
|
| 45 |
$sort_opts{Keys} = $opt{k} if($opt{k}); |
| 46 |
$sort_opts{IgnoreCase} = 1 if($opt{i}); |
| 47 |
$sort_opts{NormaliseKeySpace} = 1 if($opt{s}); |
| 48 |
$sort_opts{TempDir} = $opt{t} if($opt{t}); |
| 49 |
$sort_opts{MaxMem} = $opt{m} if($opt{m}); |
| 50 |
|
| 51 |
|
| 52 |
############################################################################## |
| 53 |
# Create a filter pipeline and 'run' it |
| 54 |
# |
| 55 |
|
| 56 |
my $writer = XML::SAX::Writer->new( Output => \*STDOUT ); |
| 57 |
my $sorter = XML::Filter::Sort->new( %sort_opts, Handler => $writer ); |
| 58 |
my $parser = XML::SAX::ParserFactory->parser(Handler => $sorter); |
| 59 |
|
| 60 |
my $fd = IO::File->new("<$filename") || die "$!"; |
| 61 |
|
| 62 |
$parser->parse_file($fd); |
| 63 |
|
| 64 |
print "\n"; |
| 65 |
|
| 66 |
exit; |
| 67 |
|
| 68 |
__END__ |
| 69 |
|
| 70 |
=head1 NAME |
| 71 |
|
| 72 |
xmlsort - sorts 'records' in XML files |
| 73 |
|
| 74 |
=head1 SYNOPSIS |
| 75 |
|
| 76 |
xmlsort -r=<recordname> [ <other options> ] [ <filename> ] |
| 77 |
|
| 78 |
Options: |
| 79 |
-r <name> name of the elements to be sorted |
| 80 |
-k <keys> child nodes to be used as sort keys |
| 81 |
-i ignore case when sorting |
| 82 |
-s normalise whitespace when comparing sort keys |
| 83 |
-t <dir> buffer records to named directory rather than in memory |
| 84 |
-m <bytes> set memory chunk size for disk buffering |
| 85 |
-h help - display the full documentation |
| 86 |
|
| 87 |
Example: |
| 88 |
xmlsort -r 'person' -k 'lastname;firstname' -i -s in.xml >out.xml |
| 89 |
|
| 90 |
=head1 DESCRIPTION |
| 91 |
|
| 92 |
This script takes an XML document either on STDIN or from a named file and |
| 93 |
writes a sorted version of the file to STDOUT. The C<-r> option should be used |
| 94 |
to identify 'records' in the document - the bits you want sorted. Elements |
| 95 |
before and after the records will be unaffected by the sort. |
| 96 |
|
| 97 |
=head1 OPTIONS |
| 98 |
|
| 99 |
Here is a brief summary of the command line options (and the XML::Filter::Sort |
| 100 |
options which they correspond to). For more details see L<XML::Filter::Sort>. |
| 101 |
|
| 102 |
=over 4 |
| 103 |
|
| 104 |
=item -r <recordname> (Record) |
| 105 |
|
| 106 |
The name of the elements to be sorted. This can be a simple element name like |
| 107 |
C<'person'> or a pathname like C<'employees/person'> (only person elements |
| 108 |
contained directly within an employees element). |
| 109 |
|
| 110 |
=item -k <keys> (Keys) |
| 111 |
|
| 112 |
Semicolon separated list of elements (or attributes) within a record which |
| 113 |
should be used as sort keys. Each key can optionally be followed by 'alpha' or |
| 114 |
'num' to indicate alphanumeric of numeric sorting and 'asc' or 'desc' for |
| 115 |
ascending or descending order (eg: -k 'lastname;firstname;age,n,d'). |
| 116 |
|
| 117 |
=item -i (IgnoreCase) |
| 118 |
|
| 119 |
This option makes sort comparisons case insensitive. |
| 120 |
|
| 121 |
=item -s (NormaliseKeySpace) |
| 122 |
|
| 123 |
By default all whitespace in the sort key elements is considered significant. |
| 124 |
Specifying -s will case leading and trailing whitespace to be stripped and |
| 125 |
internal whitespace runs to be collapsed to a single space. |
| 126 |
|
| 127 |
=item -t <directory> (TempDir) |
| 128 |
|
| 129 |
When sorting large documents, it may be prudent to use disk buffering rather |
| 130 |
than memory buffering. This option allows you to specify where temporary |
| 131 |
files should be written. |
| 132 |
|
| 133 |
=item -m <bytes> (MaxMem) |
| 134 |
|
| 135 |
If you use the -t option to enable disk buffering, records will be collected |
| 136 |
in memory in 'chunks' of up to about 10 megabytes before being sorted and |
| 137 |
spooled to temporary files. This option allows you to specify a larger |
| 138 |
chunk size. A suffix of K or M indicates kilobytes or megabytes respectively. |
| 139 |
|
| 140 |
=back |
| 141 |
|
| 142 |
=head1 SEE ALSO |
| 143 |
|
| 144 |
This script uses the following modules: |
| 145 |
|
| 146 |
XML::SAX::ParserFactory |
| 147 |
XML::Filter::Sort |
| 148 |
XML::SAX::Writer |
| 149 |
|
| 150 |
=head1 AUTHOR |
| 151 |
|
| 152 |
Grant McLean <[email protected]> |
| 153 |
|
| 154 |
=head1 COPYRIGHT |
| 155 |
|
| 156 |
Copyright (c) 2002 Grant McLean. All rights reserved. This program is |
| 157 |
free software; you can redistribute it and/or modify it under the same terms |
| 158 |
as Perl itself. |
| 159 |
|
| 160 |
=cut |
| 161 |
|
| 162 |
|
| 163 |
|