package SQL::Translator;
# ----------------------------------------------------------------------
-# $Id: Translator.pm,v 1.14 2002-11-26 03:59:57 kycl4rk Exp $
+# $Id: Translator.pm,v 1.50 2004-02-02 20:30:35 allenday Exp $
# ----------------------------------------------------------------------
-# Copyright (C) 2002 Ken Y. Clark <kclark@cpan.org>,
-# darren chamberlain <darren@cpan.org>
+# Copyright (C) 2003 Ken Y. Clark <kclark@cpan.org>,
+# darren chamberlain <darren@cpan.org>,
+# Chris Mungall <cjm@fruitfly.org>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License as
# 02111-1307 USA
# -------------------------------------------------------------------
-=head1 NAME
-
-SQL::Translator - convert schema from one database to another
-
-=head1 SYNOPSIS
-
- use SQL::Translator;
-
- my $translator = SQL::Translator->new(
- xlate => $xlate || {}, # Overrides for field translation
- debug => $debug, # Print debug info
- trace => $trace, # Print Parse::RecDescent trace
- no_comments => $no_comments, # Don't include comments in output
- show_warnings => $show_warnings, # Print name mutations, conflicts
- add_drop_table => $add_drop_table, # Add "drop table" statements
- );
-
- my $output = $translator->translate(
- from => "MySQL",
- to => "Oracle",
- filename => $file,
- ) or die $translator->error;
-
- print $output;
-
-=head1 DESCRIPTION
-
-This module attempts to simplify the task of converting one database
-create syntax to another through the use of Parsers (which understand
-the sourced format) and Producers (which understand the destination
-format). The idea is that any Parser can be used with any Producer in
-the conversion process. So, if you wanted PostgreSQL-to-Oracle, you
-would use the PostgreSQL parser and the Oracle producer.
-
-=cut
-
use strict;
use vars qw( $VERSION $REVISION $DEFAULT_SUB $DEBUG $ERROR );
use base 'Class::Base';
-$VERSION = '0.01';
-$REVISION = sprintf "%d.%02d", q$Revision: 1.14 $ =~ /(\d+)\.(\d+)/;
+require 5.004;
+
+$VERSION = '0.04';
+$REVISION = sprintf "%d.%02d", q$Revision: 1.50 $ =~ /(\d+)\.(\d+)/;
$DEBUG = 0 unless defined $DEBUG;
$ERROR = "";
use Carp qw(carp);
+use Data::Dumper;
+use Class::Base;
+use File::Find;
use File::Spec::Functions qw(catfile);
use File::Basename qw(dirname);
use IO::Dir;
+use SQL::Translator::Schema;
# ----------------------------------------------------------------------
# The default behavior is to "pass through" values (note that the
# SQL::Translator instance is the first value ($_[0]), and the stuff
# to be parsed is the second value ($_[1])
# ----------------------------------------------------------------------
-$DEFAULT_SUB = sub { $_[1] } unless defined $DEFAULT_SUB;
-
-=head1 CONSTRUCTOR
-
-The constructor is called B<new>, and accepts a optional hash of options.
-Valid options are:
-
-=over 4
-
-=item parser (aka from)
-
-=item parser_args
-
-=item producer (aka to)
-
-=item producer_args
-
-=item filename (aka file)
-
-=item data
-
-=item debug
-
-=back
-
-All options are, well, optional; these attributes can be set via
-instance methods. Internally, they are; no (non-syntactical)
-advantage is gained by passing options to the constructor.
-
-=cut
+$DEFAULT_SUB = sub { $_[0]->schema } unless defined $DEFAULT_SUB;
# ----------------------------------------------------------------------
# init([ARGS])
# ----------------------------------------------------------------------
sub init {
my ( $self, $config ) = @_;
-
#
# Set the parser and producer.
#
$self->parser ($config->{'parser'} || $config->{'from'} || $DEFAULT_SUB);
$self->producer($config->{'producer'} || $config->{'to'} || $DEFAULT_SUB);
+ #
+ # Set up callbacks for formatting of pk,fk,table,package names in producer
+ #
+ $self->format_table_name($config->{'format_table_name'});
+ $self->format_package_name($config->{'format_package_name'});
+ $self->format_fk_name($config->{'format_fk_name'});
+ $self->format_pk_name($config->{'format_pk_name'});
+
#
# Set the parser_args and producer_args
#
#
$self->{'debug'} = defined $config->{'debug'} ? $config->{'debug'} : $DEBUG;
-
$self->add_drop_table( $config->{'add_drop_table'} );
- $self->custom_translate( $config->{'xlate'} );
-
$self->no_comments( $config->{'no_comments'} );
$self->show_warnings( $config->{'show_warnings'} );
$self->trace( $config->{'trace'} );
+ $self->validate( $config->{'validate'} );
+
return $self;
}
-=head1 METHODS
-
# ----------------------------------------------------------------------
-=head2 B<add_drop_table>
-
-Toggles whether or not to add "DROP TABLE" statements just before the
-create definitions.
-
-=cut
-
+# add_drop_table([$bool])
+# ----------------------------------------------------------------------
sub add_drop_table {
my $self = shift;
if ( defined (my $arg = shift) ) {
return $self->{'add_drop_table'} || 0;
}
-
# ----------------------------------------------------------------------
-=head2 B<custom_translate>
-
-Allows the user to override default translation of fields. For example,
-if a MySQL "text" field would normally be converted to a "long" for Oracle,
-the user could specify to change it to a "CLOB." Accepts a hashref where
-keys are the "from" value and values are the "to," returns the current
-value of the field.
-
-=cut
-
-sub custom_translate {
- my $self = shift;
- $self->{'custom_translate'} = shift if @_;
- return $self->{'custom_translate'} || {};
-}
-
+# no_comments([$bool])
# ----------------------------------------------------------------------
-=head2 B<no_comments>
-
-Toggles whether to print comments in the output. Accepts a true or false
-value, returns the current value.
-
-=cut
-
sub no_comments {
my $self = shift;
my $arg = shift;
return $self->{'no_comments'} || 0;
}
-# ----------------------------------------------------------------------
-=head2 B<producer>
-
-The B<producer> method is an accessor/mutator, used to retrieve or
-define what subroutine is called to produce the output. A subroutine
-defined as a producer will be invoked as a function (not a method) and
-passed 2 parameters: its container SQL::Translator instance and a
-data structure. It is expected that the function transform the data
-structure to a string. The SQL::Transformer instance is provided for
-informational purposes; for example, the type of the parser can be
-retrieved using the B<parser_type> method, and the B<error> and
-B<debug> methods can be called when needed.
-
-When defining a producer, one of several things can be passed
-in: A module name (e.g., My::Groovy::Producer), a module name
-relative to the SQL::Translator::Producer namespace (e.g., MySQL), a
-module name and function combination (My::Groovy::Producer::transmogrify),
-or a reference to an anonymous subroutine. If a full module name is
-passed in (for the purposes of this method, a string containing "::"
-is considered to be a module name), it is treated as a package, and a
-function called "produce" will be invoked: $modulename::produce. If
-$modulename cannot be loaded, the final portion is stripped off and
-treated as a function. In other words, if there is no file named
-My/Groovy/Producer/transmogrify.pm, SQL::Translator will attempt to load
-My/Groovy/Producer.pm and use transmogrify as the name of the function,
-instead of the default "produce".
-
- my $tr = SQL::Translator->new;
-
- # This will invoke My::Groovy::Producer::produce($tr, $data)
- $tr->producer("My::Groovy::Producer");
-
- # This will invoke SQL::Translator::Producer::Sybase::produce($tr, $data)
- $tr->producer("Sybase");
-
- # This will invoke My::Groovy::Producer::transmogrify($tr, $data),
- # assuming that My::Groovy::Producer::transmogrify is not a module
- # on disk.
- $tr->producer("My::Groovy::Producer::transmogrify");
-
- # This will invoke the referenced subroutine directly, as
- # $subref->($tr, $data);
- $tr->producer(\&my_producer);
-
-There is also a method named B<producer_type>, which is a string
-containing the classname to which the above B<produce> function
-belongs. In the case of anonymous subroutines, this method returns
-the string "CODE".
-
-Finally, there is a method named B<producer_args>, which is both an
-accessor and a mutator. Arbitrary data may be stored in name => value
-pairs for the producer subroutine to access:
-
- sub My::Random::producer {
- my ($tr, $data) = @_;
- my $pr_args = $tr->producer_args();
-
- # $pr_args is a hashref.
-
-Extra data passed to the B<producer> method is passed to
-B<producer_args>:
-
- $tr->producer("xSV", delimiter => ',\s*');
-
- # In SQL::Translator::Producer::xSV:
- my $args = $tr->producer_args;
- my $delimiter = $args->{'delimiter'}; # value is ,\s*
-
-=cut
-# producer and producer_type
+# ----------------------------------------------------------------------
+# producer([$producer_spec])
+#
+# Get or set the producer for the current translator.
+# ----------------------------------------------------------------------
sub producer {
my $self = shift;
# passed a string containing no "::"; relative package name
else {
+ $producer =~ s/-/::/g;
my $Pp = sprintf "SQL::Translator::Producer::$producer";
load($Pp) or die "Can't load $Pp: $@";
$self->{'producer'} = \&{ "$Pp\::produce" };
};
# ----------------------------------------------------------------------
-# producer_type
+# producer_type()
#
# producer_type is an accessor that allows producer subs to get
# information about their origin. This is poptentially important;
-# since all producer subs are called as subroutine refernces, there is
+# since all producer subs are called as subroutine references, there is
# no way for a producer to find out which package the sub lives in
# originally, for example.
# ----------------------------------------------------------------------
sub producer_type { $_[0]->{'producer_type'} }
# ----------------------------------------------------------------------
-# producer_args
+# producer_args([\%args])
#
# Arbitrary name => value pairs of paramters can be passed to a
# producer using this method.
#
-# XXX All calls to producer_args with a value clobbers old values!
-# Should probably check if $_[0] is undef, and delete stored
-# args if it is:
-#
-# if (@_) {
-# unless (defined $_[0]) {
-# %{ $self->{'producer_args'} } = ();
-# }
-# my $args = isa($_[0], 'HASH') ? shift : { @_ };
-# %{ $self->{'producer_args'} } = (
-# %{ $self->{'producer_args'} },
-# %{ $args }
-# );
-# }
+# If the first argument passed in is undef, then the hash of arguments
+# is cleared; all subsequent elements are added to the hash of name,
+# value pairs stored as producer_args.
# ----------------------------------------------------------------------
sub producer_args {
my $self = shift;
- if (@_) {
- my $args = isa($_[0], 'HASH') ? shift : { @_ };
- $self->{'producer_args'} = $args;
- }
- $self->{'producer_args'};
+ return $self->_args("producer", @_);
}
# ----------------------------------------------------------------------
-=head2 B<parser>
-
-The B<parser> method defines or retrieves a subroutine that will be
-called to perform the parsing. The basic idea is the same as that of
-B<producer> (see above), except the default subroutine name is
-"parse", and will be invoked as $module_name::parse($tr, $data).
-Also, the parser subroutine will be passed a string containing the
-entirety of the data to be parsed.
-
- # Invokes SQL::Translator::Parser::MySQL::parse()
- $tr->parser("MySQL");
-
- # Invokes My::Groovy::Parser::parse()
- $tr->parser("My::Groovy::Parser");
-
- # Invoke an anonymous subroutine directly
- $tr->parser(sub {
- my $dumper = Data::Dumper->new([ $_[1] ], [ "SQL" ]);
- $dumper->Purity(1)->Terse(1)->Deepcopy(1);
- return $dumper->Dump;
- });
-
-There is also B<parser_type> and B<parser_args>, which perform
-analogously to B<producer_type> and B<producer_args>
-
-=cut
-
+# parser([$parser_spec])
+# ----------------------------------------------------------------------
sub parser {
my $self = shift;
# passed a string containing no "::"; relative package name
else {
+ $parser =~ s/-/::/g;
my $Pp = "SQL::Translator::Parser::$parser";
load( $Pp ) or die "Can't load $Pp: $@";
$self->{'parser'} = \&{ "$Pp\::parse" };
# ----------------------------------------------------------------------
sub parser_type { $_[0]->{'parser_type'} }
-# ----------------------------------------------------------------------
-# XXX See notes on producer_args, above
sub parser_args {
my $self = shift;
- if (@_) {
- my $args = isa($_[0], 'HASH') ? shift : { @_ };
- $self->{'parser_args'} = $args;
- }
- $self->{'parser_args'};
-}
-
-# ----------------------------------------------------------------------
-=head2 B<show_warnings>
-
-Toggles whether to print warnings of name conflicts, identifier
-mutations, etc. Probably only generated by producers to let the user
-know when something won't translate very smoothly (e.g., MySQL "enum"
-fields into Oracle). Accepts a true or false value, returns the
-current value.
-
-=cut
+ return $self->_args("parser", @_);
+}
sub show_warnings {
my $self = shift;
return $self->{'show_warnings'} || 0;
}
-# ----------------------------------------------------------------------
-=head2 B<translate>
-
-The B<translate> method calls the subroutines referenced by the
-B<parser> and B<producer> data members (described above). It accepts
-as arguments a number of things, in key => value format, including
-(potentially) a parser and a producer (they are passed directly to the
-B<parser> and B<producer> methods).
-
-Here is how the parameter list to B<translate> is parsed:
-
-=over
-
-=item *
-
-1 argument means it's the data to be parsed; which could be a string
-(filename) or a refernce to a scalar (a string stored in memory), or a
-reference to a hash, which is parsed as being more than one argument
-(see next section).
-
- # Parse the file /path/to/datafile
- my $output = $tr->translate("/path/to/datafile");
-
- # Parse the data contained in the string $data
- my $output = $tr->translate(\$data);
-
-=item *
-
-More than 1 argument means its a hash of things, and it might be
-setting a parser, producer, or datasource (this key is named
-"filename" or "file" if it's a file, or "data" for a SCALAR reference.
-
- # As above, parse /path/to/datafile, but with different producers
- for my $prod ("MySQL", "XML", "Sybase") {
- print $tr->translate(
- producer => $prod,
- filename => "/path/to/datafile",
- );
- }
-
- # The filename hash key could also be:
- datasource => \$data,
-
-You get the idea.
-
-=back
-
-# ----------------------------------------------------------------------
-=head2 B<filename>, B<data>
-
-Using the B<filename> method, the filename of the data to be parsed
-can be set. This method can be used in conjunction with the B<data>
-method, below. If both the B<filename> and B<data> methods are
-invoked as mutators, the data set in the B<data> method is used.
-
- $tr->filename("/my/data/files/create.sql");
-
-or:
-
- my $create_script = do {
- local $/;
- open CREATE, "/my/data/files/create.sql" or die $!;
- <CREATE>;
- };
- $tr->data(\$create_script);
-
-B<filename> takes a string, which is interpreted as a filename.
-B<data> takes a reference to a string, which is used as the data to be
-parsed. If a filename is set, then that file is opened and read when
-the B<translate> method is called, as long as the data instance
-variable is not set.
-
-=cut
# filename - get or set the filename
sub filename {
if (-d $filename) {
my $msg = "Cannot use directory '$filename' as input source";
return $self->error($msg);
+ } elsif (ref($filename) eq 'ARRAY') {
+ $self->{'filename'} = $filename;
+ $self->debug("Got array of files: ".join(', ',@$filename)."\n");
} elsif (-f _ && -r _) {
$self->{'filename'} = $filename;
$self->debug("Got filename: '$self->{'filename'}'\n");
}
# ----------------------------------------------------------------------
-# data - get or set the data
+# data([$data])
+#
# if $self->{'data'} is not set, but $self->{'filename'} is, then
-# $self->{'filename'} is opened and read, whith the results put into
+# $self->{'filename'} is opened and read, with the results put into
# $self->{'data'}.
+# ----------------------------------------------------------------------
sub data {
my $self = shift;
- # Set $self->{'data'} to $_[0], if it is provided.
+ # Set $self->{'data'} based on what was passed in. We will
+ # accept a number of things; do our best to get it right.
if (@_) {
my $data = shift;
if (isa($data, "SCALAR")) {
$self->{'data'} = $data;
}
- elsif (! ref $data) {
+ else {
+ if (isa($data, 'ARRAY')) {
+ $data = join '', @$data;
+ }
+ elsif (isa($data, 'GLOB')) {
+ local $/;
+ $data = <$data>;
+ }
+ elsif (! ref $data && @_) {
+ $data = join '', $data, @_;
+ }
$self->{'data'} = \$data;
}
}
local $/;
my $data;
- unless (open FH, $filename) {
- return $self->error("Can't read file '$filename': $!");
- }
+ my @files = ref($filename) eq 'ARRAY' ? @$filename : ($filename);
- $data = <FH>;
- $self->{'data'} = \$data;
+ foreach my $file (@files) {
+ unless (open FH, $file) {
+ return $self->error("Can't read file '$file': $!");
+ }
- unless (close FH) {
- return $self->error("Can't close file '$filename': $!");
+ $data .= <FH>;
+
+ unless (close FH) {
+ return $self->error("Can't close file '$file': $!");
+ }
}
+
+ $self->{'data'} = \$data;
}
return $self->{'data'};
}
# ----------------------------------------------------------------------
-=pod
+sub reset {
+#
+# Deletes the existing Schema object so that future calls to translate
+# don't append to the existing.
+#
+ my $self = shift;
+ $self->{'schema'} = undef;
+ return 1;
+}
-=head2 B<trace>
+# ----------------------------------------------------------------------
+sub schema {
+#
+# Returns the SQL::Translator::Schema object
+#
+ my $self = shift;
-Turns on/off the tracing option of Parse::RecDescent.
+ unless ( defined $self->{'schema'} ) {
+ $self->{'schema'} = SQL::Translator::Schema->new;
+ }
-=cut
+ return $self->{'schema'};
+}
+# ----------------------------------------------------------------------
sub trace {
my $self = shift;
my $arg = shift;
}
# ----------------------------------------------------------------------
+# translate([source], [\%args])
+#
+# translate does the actual translation. The main argument is the
+# source of the data to be translated, which can be a filename, scalar
+# reference, or glob reference.
+#
+# Alternatively, translate takes optional arguements, which are passed
+# to the appropriate places. Most notable of these arguments are
+# parser and producer, which can be used to set the parser and
+# producer, respectively. This is the applications last chance to set
+# these.
+#
+# translate returns a string.
+# ----------------------------------------------------------------------
sub translate {
my $self = shift;
my ($args, $parser, $parser_type, $producer, $producer_type);
$args = $_[0];
}
+ # Passed a GLOB reference, i.e., filehandle
+ elsif (isa($_[0], 'GLOB')) {
+ $self->debug("translate: Got a GLOB reference\n");
+ $self->data($_[0]);
+ }
+
# Passed a reference to a string containing the data
elsif (isa($_[0], 'SCALAR')) {
# passed a ref to a string
$self->filename($filename);
}
- if (my $data = ($self->{'data'} || $self->{'datasource'})) {
+ if (my $data = ($args->{'data'} || $args->{'datasource'})) {
$self->data($data);
}
# Get the data.
# ----------------------------------------------------------------
my $data = $self->data;
- unless (length $$data) {
- return $self->error("Empty data file!");
- }
# ----------------------------------------------------------------
# Local reference to the parser subroutine
# the future, each of these might happen in a Safe environment,
# depending on how paranoid we want to be.
# ----------------------------------------------------------------
- eval { $parser_output = $parser->($self, $$data) };
- if ($@ || ! $parser_output) {
- my $msg = sprintf "translate: Error with parser '%s': %s",
- $parser_type, ($@) ? $@ : " no results";
- return $self->error($msg);
+ unless ( defined $self->{'schema'} ) {
+ eval { $parser_output = $parser->($self, $$data) };
+ if ($@ || ! $parser_output) {
+ my $msg = sprintf "translate: Error with parser '%s': %s",
+ $parser_type, ($@) ? $@ : " no results";
+ return $self->error($msg);
+ }
+ }
+
+ $self->debug("Schema =\n", Dumper($self->schema), "\n");
+
+ if ($self->validate) {
+ my $schema = $self->schema;
+ return $self->error('Invalid schema') unless $schema->is_valid;
}
- eval { $producer_output = $producer->($self, $parser_output) };
+ eval { $producer_output = $producer->($self) };
if ($@ || ! $producer_output) {
- my $msg = sprintf "translate: Error with producer '%s': %s",
- $producer_type, ($@) ? $@ : " no results";
+ my $err = $@ || $self->error || "no results";
+ my $msg = "translate: Error with producer '$producer_type': $err";
return $self->error($msg);
}
}
# ----------------------------------------------------------------------
-sub list_producers {
- require SQL::Translator::Producer;
- my $path = catfile(dirname($INC{'SQL/Translator/Producer.pm'}), "Producer");
- my $dh = IO::Dir->new($path);
-
- my @available = map { join "::", "SQL::Translator::Producer", $_ }
- grep /\.pm$/, $dh->read;
-
- return @available;
+# list_parsers()
+#
+# Hacky sort of method to list all available parsers. This has
+# several problems:
+#
+# - Only finds things in the SQL::Translator::Parser namespace
+#
+# - Only finds things that are located in the same directory
+# as SQL::Translator::Parser. Yeck.
+#
+# This method will fail in several very likely cases:
+#
+# - Parser modules in different namespaces
+#
+# - Parser modules in the SQL::Translator::Parser namespace that
+# have any XS componenets will be installed in
+# arch_lib/SQL/Translator.
+#
+# ----------------------------------------------------------------------
+sub list_parsers {
+ return shift->_list("parser");
}
# ----------------------------------------------------------------------
-sub list_parsers {
- require SQL::Translator::Parser;
- my $path = catfile(dirname($INC{'SQL/Translator/Parser.pm'}), "Parser");
- my $dh = IO::Dir->new($path);
+# list_producers()
+#
+# See notes for list_parsers(), above; all the problems apply to
+# list_producers as well.
+# ----------------------------------------------------------------------
+sub list_producers {
+ return shift->_list("producer");
+}
+
+
+# ======================================================================
+# Private Methods
+# ======================================================================
+
+# ----------------------------------------------------------------------
+# _args($type, \%args);
+#
+# Gets or sets ${type}_args. Called by parser_args and producer_args.
+# ----------------------------------------------------------------------
+sub _args {
+ my $self = shift;
+ my $type = shift;
+ $type = "${type}_args" unless $type =~ /_args$/;
+
+ unless (defined $self->{$type} && isa($self->{$type}, 'HASH')) {
+ $self->{$type} = { };
+ }
+
+ if (@_) {
+ # If the first argument is an explicit undef (remember, we
+ # don't get here unless there is stuff in @_), then we clear
+ # out the producer_args hash.
+ if (! defined $_[0]) {
+ shift @_;
+ %{$self->{$type}} = ();
+ }
- my @available = map { join "::", "SQL::Translator::Parser", $_ }
- grep /\.pm$/, $dh->read;
+ my $args = isa($_[0], 'HASH') ? shift : { @_ };
+ %{$self->{$type}} = (%{$self->{$type}}, %$args);
+ }
- return @available;
+ $self->{$type};
}
# ----------------------------------------------------------------------
+# _list($type)
+# ----------------------------------------------------------------------
+sub _list {
+ my $self = shift;
+ my $type = shift || return ();
+ my $uctype = ucfirst lc $type;
+
+ #
+ # First find all the directories where SQL::Translator
+ # parsers or producers (the "type") appear to live.
+ #
+ load("SQL::Translator::$uctype") or return ();
+ my $path = catfile "SQL", "Translator", $uctype;
+ my @dirs;
+ for (@INC) {
+ my $dir = catfile $_, $path;
+ $self->debug("_list_${type}s searching $dir\n");
+ next unless -d $dir;
+ push @dirs, $dir;
+ }
+
+ #
+ # Now use File::File::find to look recursively in those
+ # directories for all the *.pm files, then present them
+ # with the slashes turned into dashes.
+ #
+ my %found;
+ find(
+ sub {
+ if ( -f && m/\.pm$/ ) {
+ my $mod = $_;
+ $mod =~ s/\.pm$//;
+ my $cur_dir = $File::Find::dir;
+ my $base_dir = quotemeta catfile 'SQL', 'Translator', $uctype;
+
+ #
+ # See if the current directory is below the base directory.
+ #
+ if ( $cur_dir =~ m/$base_dir(.*)/ ) {
+ $cur_dir = $1;
+ $cur_dir =~ s!^/!!; # kill leading slash
+ $cur_dir =~ s!/!-!g; # turn other slashes into dashes
+ }
+ else {
+ $cur_dir = '';
+ }
+
+ $found{ join '-', map { $_ || () } $cur_dir, $mod } = 1;
+ }
+ },
+ @dirs
+ );
+
+ return sort { lc $a cmp lc $b } keys %found;
+}
+
+# ----------------------------------------------------------------------
+# load($module)
+#
+# Loads a Perl module. Short circuits if a module is already loaded.
+# ----------------------------------------------------------------------
sub load {
my $module = do { my $m = shift; $m =~ s[::][/]g; "$m.pm" };
return 1 if $INC{$module};
-
- eval { require $module };
-
- return if ($@);
+
+ eval {
+ require $module;
+ $module->import(@_);
+ };
+
+ return __PACKAGE__->error($@) if ($@);
return 1;
}
# ----------------------------------------------------------------------
-sub isa { UNIVERSAL::isa($_[0], $_[1]) }
+sub format_table_name {
+ return shift->_format_name('_format_table_name', @_);
+}
+
+# ----------------------------------------------------------------------
+sub format_package_name {
+ return shift->_format_name('_format_package_name', @_);
+}
+
+# ----------------------------------------------------------------------
+sub format_fk_name {
+ return shift->_format_name('_format_fk_name', @_);
+}
+
+# ----------------------------------------------------------------------
+sub format_pk_name {
+ return shift->_format_name('_format_pk_name', @_);
+}
+
+# ----------------------------------------------------------------------
+# The other format_*_name methods rely on this one. It optionally
+# accepts a subroutine ref as the first argument (or uses an identity
+# sub if one isn't provided or it doesn't already exist), and applies
+# it to the rest of the arguments (if any).
+# ----------------------------------------------------------------------
+sub _format_name {
+ my $self = shift;
+ my $field = shift;
+ my @args = @_;
+
+ if (ref($args[0]) eq 'CODE') {
+ $self->{$field} = shift @args;
+ }
+ elsif (! exists $self->{$field}) {
+ $self->{$field} = sub { return shift };
+ }
+
+ return @args ? $self->{$field}->(@args) : $self->{$field};
+}
+
+# ----------------------------------------------------------------------
+# isa($ref, $type)
+#
+# Calls UNIVERSAL::isa($ref, $type). I think UNIVERSAL::isa is ugly,
+# but I like function overhead.
+# ----------------------------------------------------------------------
+sub isa($$) {
+ my ($ref, $type) = @_;
+ return UNIVERSAL::isa($ref, $type);
+}
+
+# ----------------------------------------------------------------------
+sub validate {
+ my ( $self, $arg ) = @_;
+ if ( defined $arg ) {
+ $self->{'validate'} = $arg ? 1 : 0;
+ }
+ return $self->{'validate'} || 0;
+}
1;
-#-----------------------------------------------------
-# Rescue the drowning and tie your shoestrings.
-# Henry David Thoreau
-#-----------------------------------------------------
+# ----------------------------------------------------------------------
+# Who killed the pork chops?
+# What price bananas?
+# Are you my Angel?
+# Allen Ginsberg
+# ----------------------------------------------------------------------
=pod
+=head1 NAME
+
+SQL::Translator - manipulate structured data definitions (SQL and more)
+
+=head1 SYNOPSIS
+
+ use SQL::Translator;
+
+ my $translator = SQL::Translator->new(
+ # Print debug info
+ debug => 1,
+ # Print Parse::RecDescent trace
+ trace => 0,
+ # Don't include comments in output
+ no_comments => 0,
+ # Print name mutations, conflicts
+ show_warnings => 0,
+ # Add "drop table" statements
+ add_drop_table => 1,
+ # Validate schema object
+ validate => 1,
+ # Make all table names CAPS in producers which support this option
+ format_table_name => sub {my $tablename = shift; return uc($tablename)},
+ # Null-op formatting, only here for documentation's sake
+ format_package_name => sub {return shift},
+ format_fk_name => sub {return shift},
+ format_pk_name => sub {return shift},
+ );
+
+ my $output = $translator->translate(
+ from => 'MySQL',
+ to => 'Oracle',
+ # Or an arrayref of filenames, i.e. [ $file1, $file2, $file3 ]
+ filename => $file,
+ ) or die $translator->error;
+
+ print $output;
+
+=head1 DESCRIPTION
+
+SQL::Translator is a group of Perl modules that converts
+vendor-specific SQL table definitions into other formats, such as
+other vendor-specific SQL, ER diagrams, documentation (POD and HTML),
+XML, and Class::DBI classes. The main focus of SQL::Translator is
+SQL, but parsers exist for other structured data formats, including
+Excel spreadsheets and arbitrarily delimited text files. Through the
+separation of the code into parsers and producers with an object model
+in between, it's possible to combine any parser with any producer, to
+plug in custom parsers or producers, or to manipulate the parsed data
+via the built-in object model. Presently only the definition parts of
+SQL are handled (CREATE, ALTER), not the manipulation of data (INSERT,
+UPDATE, DELETE).
+
+=head1 CONSTRUCTOR
+
+The constructor is called C<new>, and accepts a optional hash of options.
+Valid options are:
+
+=over 4
+
+=item *
+
+parser / from
+
+=item *
+
+parser_args
+
+=item *
+
+producer / to
+
+=item *
+
+producer_args
+
+=item *
+
+filename / file
+
+=item *
+
+data
+
+=item *
+
+debug
+
+=item *
+
+add_drop_table
+
+=item *
+
+no_comments
+
+=item *
+
+trace
+
+=item *
+
+validate
+
+=back
+
+All options are, well, optional; these attributes can be set via
+instance methods. Internally, they are; no (non-syntactical)
+advantage is gained by passing options to the constructor.
+
+=head1 METHODS
+
+=head2 add_drop_table
+
+Toggles whether or not to add "DROP TABLE" statements just before the
+create definitions.
+
+=head2 no_comments
+
+Toggles whether to print comments in the output. Accepts a true or false
+value, returns the current value.
+
+=head2 producer
+
+The C<producer> method is an accessor/mutator, used to retrieve or
+define what subroutine is called to produce the output. A subroutine
+defined as a producer will be invoked as a function (I<not a method>)
+and passed 2 parameters: its container C<SQL::Translator> instance and a
+data structure. It is expected that the function transform the data
+structure to a string. The C<SQL::Transformer> instance is provided for
+informational purposes; for example, the type of the parser can be
+retrieved using the C<parser_type> method, and the C<error> and
+C<debug> methods can be called when needed.
+
+When defining a producer, one of several things can be passed in: A
+module name (e.g., C<My::Groovy::Producer>), a module name relative to
+the C<SQL::Translator::Producer> namespace (e.g., C<MySQL>), a module
+name and function combination (C<My::Groovy::Producer::transmogrify>),
+or a reference to an anonymous subroutine. If a full module name is
+passed in (for the purposes of this method, a string containing "::"
+is considered to be a module name), it is treated as a package, and a
+function called "produce" will be invoked: C<$modulename::produce>.
+If $modulename cannot be loaded, the final portion is stripped off and
+treated as a function. In other words, if there is no file named
+F<My/Groovy/Producer/transmogrify.pm>, C<SQL::Translator> will attempt
+to load F<My/Groovy/Producer.pm> and use C<transmogrify> as the name of
+the function, instead of the default C<produce>.
+
+ my $tr = SQL::Translator->new;
+
+ # This will invoke My::Groovy::Producer::produce($tr, $data)
+ $tr->producer("My::Groovy::Producer");
+
+ # This will invoke SQL::Translator::Producer::Sybase::produce($tr, $data)
+ $tr->producer("Sybase");
+
+ # This will invoke My::Groovy::Producer::transmogrify($tr, $data),
+ # assuming that My::Groovy::Producer::transmogrify is not a module
+ # on disk.
+ $tr->producer("My::Groovy::Producer::transmogrify");
+
+ # This will invoke the referenced subroutine directly, as
+ # $subref->($tr, $data);
+ $tr->producer(\&my_producer);
+
+There is also a method named C<producer_type>, which is a string
+containing the classname to which the above C<produce> function
+belongs. In the case of anonymous subroutines, this method returns
+the string "CODE".
+
+Finally, there is a method named C<producer_args>, which is both an
+accessor and a mutator. Arbitrary data may be stored in name => value
+pairs for the producer subroutine to access:
+
+ sub My::Random::producer {
+ my ($tr, $data) = @_;
+ my $pr_args = $tr->producer_args();
+
+ # $pr_args is a hashref.
+
+Extra data passed to the C<producer> method is passed to
+C<producer_args>:
+
+ $tr->producer("xSV", delimiter => ',\s*');
+
+ # In SQL::Translator::Producer::xSV:
+ my $args = $tr->producer_args;
+ my $delimiter = $args->{'delimiter'}; # value is ,\s*
+
+=head2 parser
+
+The C<parser> method defines or retrieves a subroutine that will be
+called to perform the parsing. The basic idea is the same as that of
+C<producer> (see above), except the default subroutine name is
+"parse", and will be invoked as C<$module_name::parse($tr, $data)>.
+Also, the parser subroutine will be passed a string containing the
+entirety of the data to be parsed.
+
+ # Invokes SQL::Translator::Parser::MySQL::parse()
+ $tr->parser("MySQL");
+
+ # Invokes My::Groovy::Parser::parse()
+ $tr->parser("My::Groovy::Parser");
+
+ # Invoke an anonymous subroutine directly
+ $tr->parser(sub {
+ my $dumper = Data::Dumper->new([ $_[1] ], [ "SQL" ]);
+ $dumper->Purity(1)->Terse(1)->Deepcopy(1);
+ return $dumper->Dump;
+ });
+
+There is also C<parser_type> and C<parser_args>, which perform
+analogously to C<producer_type> and C<producer_args>
+
+=head2 show_warnings
+
+Toggles whether to print warnings of name conflicts, identifier
+mutations, etc. Probably only generated by producers to let the user
+know when something won't translate very smoothly (e.g., MySQL "enum"
+fields into Oracle). Accepts a true or false value, returns the
+current value.
+
+=head2 translate
+
+The C<translate> method calls the subroutines referenced by the
+C<parser> and C<producer> data members (described above). It accepts
+as arguments a number of things, in key => value format, including
+(potentially) a parser and a producer (they are passed directly to the
+C<parser> and C<producer> methods).
+
+Here is how the parameter list to C<translate> is parsed:
+
+=over
+
+=item *
+
+1 argument means it's the data to be parsed; which could be a string
+(filename) or a reference to a scalar (a string stored in memory), or a
+reference to a hash, which is parsed as being more than one argument
+(see next section).
+
+ # Parse the file /path/to/datafile
+ my $output = $tr->translate("/path/to/datafile");
+
+ # Parse the data contained in the string $data
+ my $output = $tr->translate(\$data);
+
+=item *
+
+More than 1 argument means its a hash of things, and it might be
+setting a parser, producer, or datasource (this key is named
+"filename" or "file" if it's a file, or "data" for a SCALAR reference.
+
+ # As above, parse /path/to/datafile, but with different producers
+ for my $prod ("MySQL", "XML", "Sybase") {
+ print $tr->translate(
+ producer => $prod,
+ filename => "/path/to/datafile",
+ );
+ }
+
+ # The filename hash key could also be:
+ datasource => \$data,
+
+You get the idea.
+
+=back
+
+=head2 filename, data
+
+Using the C<filename> method, the filename of the data to be parsed
+can be set. This method can be used in conjunction with the C<data>
+method, below. If both the C<filename> and C<data> methods are
+invoked as mutators, the data set in the C<data> method is used.
+
+ $tr->filename("/my/data/files/create.sql");
+
+or:
+
+ my $create_script = do {
+ local $/;
+ open CREATE, "/my/data/files/create.sql" or die $!;
+ <CREATE>;
+ };
+ $tr->data(\$create_script);
+
+C<filename> takes a string, which is interpreted as a filename.
+C<data> takes a reference to a string, which is used as the data to be
+parsed. If a filename is set, then that file is opened and read when
+the C<translate> method is called, as long as the data instance
+variable is not set.
+
+=head2 schema
+
+Returns the SQL::Translator::Schema object.
+
+=head2 trace
+
+Turns on/off the tracing option of Parse::RecDescent.
+
+=head2 validate
+
+Whether or not to validate the schema object after parsing and before
+producing.
+
=head1 AUTHORS
-Ken Y. Clark, E<lt>kclark@cpan.org<gt>,
-darren chamberlain E<lt>darren@cpan.orgE<gt>,
-Chris Mungall E<lt>cjm@fruitfly.orgE<gt>
+The following people have contributed to the SQLFairy project:
+
+=over 4
+
+=item * Mark Addison <grommit@users.sourceforge.net>
+
+=item * Sam Angiuoli <angiuoli@users.sourceforge.net>
+
+=item * Dave Cash <dave@gnofn.org>
+
+=item * Darren Chamberlain <dlc@users.sourceforge.net>
+
+=item * Ken Y. Clark <kclark@cpan.org>
+
+=item * Allen Day <allenday@users.sourceforge.net>
+
+=item * Paul Harrington <phrrngtn@users.sourceforge.net>
+
+=item * Mikey Melillo <mmelillo@users.sourceforge.net>
+
+=item * Chris Mungall <cjm@fruitfly.org>
+
+=item * Ross Smith II <rossta@users.sf.net>
+
+=item * Gudmundur A. Thorisson <mummi@cshl.org>
+
+=item * Chris To <christot@users.sourceforge.net>
+
+=item * Jason Williams <smdwilliams@users.sourceforge.net>
+
+=item * Ying Zhang <zyolive@yahoo.com>
+
+=back
+
+If you would like to contribute to the project, you can send patches
+to the developers mailing list:
+
+ sqlfairy-developers@lists.sourceforge.net
+
+Or send us a message (with your Sourceforge username) asking to be
+added to the project and what you'd like to contribute.
+
=head1 COPYRIGHT
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
USA
-=head1 SEE ALSO
+=head1 BUGS
-L<perl>, L<Parse::RecDescent>
+Please use L<http://rt.cpan.org/> for reporting bugs.
+
+=head1 PRAISE
+
+If you find this module useful, please use
+L<http://cpanratings.perl.org/rate/?distribution=SQL-Translator> to rate it.
+
+=head1 SEE ALSO
-=cut
+L<perl>,
+L<SQL::Translator::Parser>,
+L<SQL::Translator::Producer>,
+L<Parse::RecDescent>,
+L<GD>,
+L<GraphViz>,
+L<Text::RecordParser>,
+L<Class::DBI>,
+L<XML::Writer>.