1 package SQL::Translator::Parser::xSV;
3 # -------------------------------------------------------------------
4 # Copyright (C) 2002-2009 SQLFairy Authors
6 # This program is free software; you can redistribute it and/or
7 # modify it under the terms of the GNU General Public License as
8 # published by the Free Software Foundation; version 2.
10 # This program is distributed in the hope that it will be useful, but
11 # WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 # General Public License for more details.
15 # You should have received a copy of the GNU General Public License
16 # along with this program; if not, write to the Free Software
17 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
19 # -------------------------------------------------------------------
23 SQL::Translator::Parser::xSV - parser for arbitrarily delimited text files
28 use SQL::Translator::Parser::xSV;
30 my $translator = SQL::Translator->new(
32 parser_args => { field_separator => "\t" },
37 Parses arbitrarily delimited text files. See the
38 Text::RecordParser manpage for arguments on how to parse the file
39 (e.g., C<field_separator>, C<record_separator>). Other arguments
48 Indicates that the columns should be scanned to determine data types
49 and field sizes. True by default.
53 A shortcut to sending filters to Text::RecordParser, will create
54 callbacks that trim leading and trailing spaces from fields and headers.
59 Field names will automatically be normalized by
60 C<SQL::Translator::Utils::normalize_name>.
64 # -------------------------------------------------------------------
67 use vars qw($VERSION @EXPORT);
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
82 my ( $tr, $data ) = @_;
83 my $args = $tr->parser_args;
84 my $parser = Text::RecordParser->new(
85 field_separator => $args->{'field_separator'} || ',',
86 record_separator => $args->{'record_separator'} || "\n",
88 header_filter => \&normalize_name,
91 $parser->field_filter( sub { $_ = shift || ''; s/^\s+|\s+$//g; $_ } )
92 unless defined $args->{'trim_fields'} && $args->{'trim_fields'} == 0;
94 my $schema = $tr->schema;
95 my $table = $schema->add_table( name => 'table1' );
98 # Get the field names from the first row.
100 $parser->bind_header;
101 my @field_names = $parser->field_list;
103 for ( my $i = 0; $i < @field_names; $i++ ) {
104 my $field = $table->add_field(
105 name => $field_names[$i],
110 is_auto_increment => undef,
111 ) or die $table->error;
114 $table->primary_key( $field->name );
115 $field->is_primary_key(1);
120 # If directed, look at every field's values to guess size and type.
123 defined $args->{'scan_fields'} &&
124 $args->{'scan_fields'} == 0
126 my %field_info = map { $_, {} } @field_names;
127 while ( my $rec = $parser->fetchrow_hashref ) {
128 for my $field ( @field_names ) {
129 my $data = defined $rec->{ $field } ? $rec->{ $field } : '';
130 my $size = [ length $data ];
133 if ( $data =~ /^-?\d+$/ ) {
137 $data =~ /^-?[,\d]+\.[\d+]?$/
139 $data =~ /^-?[,\d]+?\.\d+$/
145 map { s/,//g; length $_ || 1 } split( /\./, $data );
146 $size = [ $w + $d, $d ];
153 next unless defined $size->[ $i ];
154 my $fsize = $field_info{ $field }{'size'}[ $i ] || 0;
155 if ( $size->[ $i ] > $fsize ) {
156 $field_info{ $field }{'size'}[ $i ] = $size->[ $i ];
160 $field_info{ $field }{ $type }++;
164 for my $field ( keys %field_info ) {
165 my $size = $field_info{ $field }{'size'} || [ 1 ];
167 $field_info{ $field }{'char'} ? 'char' :
168 $field_info{ $field }{'float'} ? 'float' :
169 $field_info{ $field }{'integer'} ? 'integer' : 'char';
171 if ( $data_type eq 'char' && scalar @$size == 2 ) {
172 $size = [ $size->[0] + $size->[1] ];
175 my $field = $table->get_field( $field );
176 $field->size( $size );
177 $field->data_type( $data_type );
186 # -------------------------------------------------------------------
191 Darren Chamberlain E<lt>darren@cpan.orgE<gt>,
192 Ken Y. Clark E<lt>kclark@cpan.orgE<gt>.
196 Text::RecordParser, SQL::Translator.