1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
|
package SQL::Translator::Parser::Excel;
# -------------------------------------------------------------------
# $Id: Excel.pm,v 1.14 2004/02/09 22:23:40 kycl4rk Exp $
# -------------------------------------------------------------------
# Copyright (C) 2002-4 SQLFairy Authors
#
# 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 the Free Software Foundation; version 2.
#
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
# 02111-1307 USA
# -------------------------------------------------------------------
=head1 NAME
SQL::Translator::Parser::Excel - parser for Excel
=head1 SYNOPSIS
use SQL::Translator;
my $translator = SQL::Translator->new;
$translator->parser('Excel');
=head1 DESCRIPTION
Parses an Excel spreadsheet file using Spreadsheet::ParseExcel.
=head1 OPTIONS
=over
=item * scan_fields
Indicates that the columns should be scanned to determine data types
and field sizes. True by default.
=back
=cut
use strict;
use vars qw($DEBUG $VERSION @EXPORT_OK);
$DEBUG = 0 unless defined $DEBUG;
$VERSION = sprintf "%d.%02d", q$Revision: 1.14 $ =~ /(\d+)\.(\d+)/;
use Spreadsheet::ParseExcel;
use Exporter;
use SQL::Translator::Utils qw(debug normalize_name);
use base qw(Exporter);
@EXPORT_OK = qw(parse);
my %ET_to_ST = (
'Text' => 'VARCHAR',
'Date' => 'DATETIME',
'Numeric' => 'DOUBLE',
);
# -------------------------------------------------------------------
# parse($tr, $data)
#
# Note that $data, in the case of this parser, is unuseful.
# Spreadsheet::ParseExcel works on files, not data streams.
# -------------------------------------------------------------------
sub parse {
my ($tr, $data) = @_;
my $args = $tr->parser_args;
my $filename = $tr->filename || return;
my $wb = Spreadsheet::ParseExcel::Workbook->Parse( $filename );
my $schema = $tr->schema;
my $table_no = 0;
my $wb_count = $wb->{'SheetCount'} || 0;
for my $num ( 0 .. $wb_count - 1 ) {
$table_no++;
my $ws = $wb->Worksheet( $num );
my $table_name = normalize_name( $ws->{'Name'} || "Table$table_no" );
my @cols = $ws->ColRange;
next unless $cols[1] > 0;
my $table = $schema->add_table( name => $table_name );
my @field_names = ();
for my $col ( $cols[0] .. $cols[1] ) {
my $cell = $ws->Cell(0, $col);
my $col_name = normalize_name( $cell->{'Val'} );
my $data_type = ET_to_ST( $cell->{'Type'} );
push @field_names, $col_name;
my $field = $table->add_field(
name => $col_name,
data_type => $data_type,
default_value => '',
size => 255,
is_nullable => 1,
is_auto_increment => undef,
) or die $table->error;
if ( $col == 0 ) {
$table->primary_key( $field->name );
$field->is_primary_key(1);
}
}
#
# If directed, look at every field's values to guess size and type.
#
unless (
defined $args->{'scan_fields'} &&
$args->{'scan_fields'} == 0
) {
my %field_info = map { $_, {} } @field_names;
for(
my $iR = $ws->{'MinRow'} == 0 ? 1 : $ws->{'MinRow'};
defined $ws->{'MaxRow'} && $iR <= $ws->{'MaxRow'};
$iR++
) {
for (
my $iC = $ws->{'MinCol'};
defined $ws->{'MaxCol'} && $iC <= $ws->{'MaxCol'};
$iC++
) {
my $field = $field_names[ $iC ];
my $data = $ws->{'Cells'}[ $iR ][ $iC ]->{'_Value'};
next if !defined $data || $data eq '';
my $size = [ length $data ];
my $type;
if ( $data =~ /^-?\d+$/ ) {
$type = 'integer';
}
elsif (
$data =~ /^-?[,\d]+\.[\d+]?$/
||
$data =~ /^-?[,\d]+?\.\d+$/
||
$data =~ /^-?\.\d+$/
) {
$type = 'float';
my ( $w, $d ) =
map { s/,//g; length $_ || 1 }
split( /\./, $data )
;
$size = [ $w + $d, $d ];
}
else {
$type = 'char';
}
for my $i ( 0, 1 ) {
next unless defined $size->[ $i ];
my $fsize = $field_info{ $field }{'size'}[ $i ] || 0;
if ( $size->[ $i ] > $fsize ) {
$field_info{ $field }{'size'}[ $i ] = $size->[ $i ];
}
}
$field_info{ $field }{ $type }++;
}
}
for my $field ( keys %field_info ) {
my $size = $field_info{ $field }{'size'} || [ 1 ];
my $data_type =
$field_info{ $field }{'char'} ? 'char' :
$field_info{ $field }{'float'} ? 'float' :
$field_info{ $field }{'integer'} ? 'integer' : 'char';
if ( $data_type eq 'char' && scalar @$size == 2 ) {
$size = [ $size->[0] + $size->[1] ];
}
my $field = $table->get_field( $field );
$field->size( $size ) if $size;
$field->data_type( $data_type );
}
}
}
return 1;
}
# -------------------------------------------------------------------
sub ET_to_ST {
my $et = shift;
$ET_to_ST{$et} || $ET_to_ST{'Text'};
}
1;
# -------------------------------------------------------------------
# Education is an admirable thing,
# but it is as well to remember that
# nothing that is worth knowing can be taught.
# Oscar Wilde
# -------------------------------------------------------------------
=pod
=head1 AUTHORS
Mike Mellilo <mmelillo@users.sourceforge.net>,
darren chamberlain E<lt>dlc@users.sourceforge.netE<gt>,
Ken Y. Clark E<lt>kclark@cpan.orgE<gt>.
=head1 SEE ALSO
Spreadsheet::ParseExcel, SQL::Translator.
=cut
|
