1 package SQL::Translator::Parser::xSV;
3 # -------------------------------------------------------------------
4 # $Id: xSV.pm,v 1.6 2003-05-07 20:36:59 kycl4rk Exp $
5 # -------------------------------------------------------------------
6 # Copyright (C) 2003 Ken Y. Clark <kclark@cpan.org>,
7 # darren chamberlain <darren@cpan.org>
9 # This program is free software; you can redistribute it and/or
10 # modify it under the terms of the GNU General Public License as
11 # published by the Free Software Foundation; version 2.
13 # This program is distributed in the hope that it will be useful, but
14 # WITHOUT ANY WARRANTY; without even the implied warranty of
15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16 # General Public License for more details.
18 # You should have received a copy of the GNU General Public License
19 # along with this program; if not, write to the Free Software
20 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
22 # -------------------------------------------------------------------
26 SQL::Translator::Parser::xSV - parser for arbitrarily delimited text files
31 use SQL::Translator::Parser::xSV;
33 my $translator = SQL::Translator->new(
35 parser_args => { field_separator => "\t" },
40 Parses arbitrarily delimited text files. See the
41 Text::RecordParser manpage for arguments on how to parse the file
42 (e.g., C<field_separator>, C<record_separator>). Other arguments
49 Indicates that the columns should be scanned to determine data types
54 A shortcut to sending filters to Text::RecordParser, will create
55 callbacks that trim leading and trailing spaces from fields and headers.
59 Field names will automatically be normalized by
60 C<SQL::Translator::Utils::normalize>.
64 # -------------------------------------------------------------------
67 use vars qw($VERSION @EXPORT);
68 $VERSION = sprintf "%d.%02d", q$Revision: 1.6 $ =~ /(\d+)\.(\d+)/;
71 use Text::ParseWords qw(quotewords);
72 use Text::RecordParser;
73 use SQL::Translator::Utils qw(debug normalize_name);
75 use base qw(Exporter);
79 # Passed a SQL::Translator instance and a string containing the data
84 my $args = $tr->parser_args;
85 my $parser = Text::RecordParser->new(
86 field_separator => $args->{'field_separator'} || ',',
87 record_separator => $args->{'record_separator'} || "\n",
89 header_filter => \&normalize_name,
92 $parser->field_filter( sub { $_ = shift; s/^\s+|\s+$//g; $_ } )
93 if $args->{'trim_fields'};
96 # Create skeleton structure, mostly empty.
107 # Get the field names from the first row.
109 $parser->bind_header;
110 my @field_names = $parser->field_list;
112 for ( my $i = 0; $i < @field_names; $i++ ) {
113 $parsed->{'table1'}{'fields'}{ $field_names[$i] } = {
116 name => $field_names[$i],
118 # Default datatype is "char"
121 # default size is 8bits; something more reasonable?
125 is_auto_inc => undef,
127 # field field is the primary key
128 is_primary_key => ($i == 0) ? 1 : undef,
133 # If directed, look at every field's values to guess size and type.
135 if ( $args->{'scan_fields'} ) {
136 my %field_info = map { $_, {} } @field_names;
137 while ( my $rec = $parser->fetchrow_hashref ) {
138 for my $field ( @field_names ) {
139 my $data = defined $rec->{ $field } ? $rec->{ $field } : '';
140 my $size = length $data;
143 if ( $data =~ /^-?\d+$/ ) {
146 elsif ( $data =~ /^[\d.-]+$/ ) {
153 if ( $size > $field_info{ $field }{'size'} ) {
154 $field_info{ $field }{'size'} = $size;
157 $field_info{ $field }{ $type }++;
161 for my $field ( keys %field_info ) {
162 $parsed->{'table1'}{'fields'}{ $field }{'size'} =
163 [ $field_info{ $field }{'size'} ];
165 $parsed->{'table1'}{'fields'}{ $field }{'data_type'} =
166 $field_info{ $field }{'char'} ? 'char' :
167 $field_info{ $field }{'float'} ? 'float' : 'integer';
172 # Field 0 is primary key, by default, so add an index
174 for ( $parsed->{'table1'}->{'indices'}->[0] ) {
175 $_->{'type'} = 'primary_key';
176 $_->{'name'} = undef;
177 $_->{'fields'} = [ $field_names[0] ];
185 # -------------------------------------------------------------------
190 Darren Chamberlain E<lt>darren@cpan.orgE<gt>,
191 Ken Y. Clark E<lt>kclark@cpan.orgE<gt>.