X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2FSQL%2FTranslator.pm;h=96a8d5dd9e78919d0d35dfa7beaec0f743a9534d;hb=841a3f1a241cff7e2f9fbc1bdc1e84aaa0f10909;hp=d0587598f97981b73dab315991a271d59641ea35;hpb=87bf8a3a3a848482c34fd4f19d0020a6c7c97a24;p=dbsrgits%2FSQL-Translator.git diff --git a/lib/SQL/Translator.pm b/lib/SQL/Translator.pm index d058759..96a8d5d 100644 --- a/lib/SQL/Translator.pm +++ b/lib/SQL/Translator.pm @@ -1,7 +1,7 @@ package SQL::Translator; # ---------------------------------------------------------------------- -# $Id: Translator.pm,v 1.18 2003-03-04 21:20:17 kycl4rk Exp $ +# $Id: Translator.pm,v 1.42 2003-08-21 18:12:56 kycl4rk Exp $ # ---------------------------------------------------------------------- # Copyright (C) 2003 Ken Y. Clark , # darren chamberlain , @@ -26,23 +26,28 @@ use strict; use vars qw( $VERSION $REVISION $DEFAULT_SUB $DEBUG $ERROR ); use base 'Class::Base'; -$VERSION = '0.01'; -$REVISION = sprintf "%d.%02d", q$Revision: 1.18 $ =~ /(\d+)\.(\d+)/; +require 5.004; + +$VERSION = '0.02'; +$REVISION = sprintf "%d.%02d", q$Revision: 1.42 $ =~ /(\d+)\.(\d+)/; $DEBUG = 0 unless defined $DEBUG; $ERROR = ""; use Carp qw(carp); +use Data::Dumper; +use Class::Base; use File::Spec::Functions qw(catfile); use File::Basename qw(dirname); use IO::Dir; +use SQL::Translator::Schema; # ---------------------------------------------------------------------- # The default behavior is to "pass through" values (note that the # SQL::Translator instance is the first value ($_[0]), and the stuff # to be parsed is the second value ($_[1]) # ---------------------------------------------------------------------- -$DEFAULT_SUB = sub { $_[1] } unless defined $DEFAULT_SUB; +$DEFAULT_SUB = sub { $_[0]->schema } unless defined $DEFAULT_SUB; # ---------------------------------------------------------------------- # init([ARGS]) @@ -59,7 +64,6 @@ $DEFAULT_SUB = sub { $_[1] } unless defined $DEFAULT_SUB; # ---------------------------------------------------------------------- sub init { my ( $self, $config ) = @_; - # # Set the parser and producer. # @@ -70,6 +74,14 @@ sub init { $self->parser ($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 # @@ -96,17 +108,16 @@ sub init { # $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; } @@ -121,16 +132,6 @@ sub add_drop_table { return $self->{'add_drop_table'} || 0; } - -# ---------------------------------------------------------------------- -# custom_translate([$bool]) -# ---------------------------------------------------------------------- -sub custom_translate { - my $self = shift; - $self->{'custom_translate'} = shift if @_; - return $self->{'custom_translate'} || {}; -} - # ---------------------------------------------------------------------- # no_comments([$bool]) # ---------------------------------------------------------------------- @@ -195,6 +196,7 @@ sub producer { # 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" }; @@ -287,6 +289,7 @@ sub parser { # 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" }; @@ -330,6 +333,9 @@ 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"); @@ -382,22 +388,52 @@ sub 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 = ; - $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 .= ; + + unless (close FH) { + return $self->error("Can't close file '$file': $!"); + } + } + + $self->{'data'} = \$data; } return $self->{'data'}; } +# ---------------------------------------------------------------------- +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; +} + +# ---------------------------------------------------------------------- +sub schema { +# +# Returns the SQL::Translator::Schema object +# + my $self = shift; + + unless ( defined $self->{'schema'} ) { + $self->{'schema'} = SQL::Translator::Schema->new; + } + + return $self->{'schema'}; +} +# ---------------------------------------------------------------------- sub trace { my $self = shift; my $arg = shift; @@ -483,7 +519,7 @@ sub translate { $self->filename($filename); } - if (my $data = ($self->{'data'} || $self->{'datasource'})) { + if (my $data = ($args->{'data'} || $args->{'datasource'})) { $self->data($data); } @@ -491,7 +527,7 @@ sub translate { # Get the data. # ---------------------------------------------------------------- my $data = $self->data; - unless (length $$data) { + unless (ref($data) eq 'SCALAR' and length $$data) { return $self->error("Empty data file!"); } @@ -520,14 +556,23 @@ sub translate { # 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"; @@ -558,7 +603,7 @@ sub translate { # # ---------------------------------------------------------------------- sub list_parsers { - return _list("parsers"); + return shift->_list("parser"); } # ---------------------------------------------------------------------- @@ -568,7 +613,7 @@ sub list_parsers { # list_producers as well. # ---------------------------------------------------------------------- sub list_producers { - return _list("producers"); + return shift->_list("producer"); } @@ -606,19 +651,30 @@ sub _args { $self->{$type}; } - # ---------------------------------------------------------------------- # _list($type) # ---------------------------------------------------------------------- sub _list { - my $type = ucfirst lc $_[0] || return (); - - load("SQL::Translator::$type"); - my $path = catfile(dirname($INC{'SQL/Translator/$type.pm'}), $type); - my $dh = IO::Dir->new($path); + my $self = shift; + my $type = shift || return (); + my $uctype = ucfirst lc $type; + my %found; + + load("SQL::Translator::$uctype") or return (); + my $path = catfile "SQL", "Translator", $uctype; + for (@INC) { + my $dir = catfile $_, $path; + $self->debug("_list_${type}s searching $dir\n"); + next unless -d $dir; + + my $dh = IO::Dir->new($dir); + for (grep /\.pm$/, $dh->read) { + s/\.pm$//; + $found{ join "::", "SQL::Translator::$uctype", $_ } = 1; + } + } - return map { join "::", "SQL::Translator::$type", $_ } - grep /\.pm$/, $dh->read; + return keys %found; } # ---------------------------------------------------------------------- @@ -629,14 +685,58 @@ sub _list { 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 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, @@ -647,50 +747,82 @@ sub isa($$) { 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 -#----------------------------------------------------- -__END__ +# ---------------------------------------------------------------------- +# Who killed the pork chops? +# What price bananas? +# Are you my Angel? +# Allen Ginsberg +# ---------------------------------------------------------------------- + +=pod =head1 NAME -SQL::Translator - convert schema from one database to another +SQL::Translator - manipulate structured data definitions (SQL and more) =head1 SYNOPSIS use SQL::Translator; - my $translator = SQL::Translator->new( - debug => 1, # Print debug info - trace => 0, # Print Parse::RecDescent trace - no_comments => 0, # Don't include comments in output - show_warnings => 0, # Print name mutations, conflicts - add_drop_table => 1, # Add "drop table" statements + 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", - filename => $file, + from => 'MySQL', + to => 'Oracle', + # Or an arrayref of filenames, i.e. [ $file1, $file2, $file3 ] + 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 source 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 Postgres-to-Oracle, you -would use the Postgres parser and the Oracle producer. +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 B, and accepts a optional hash of options. +The constructor is called C, and accepts a optional hash of options. Valid options are: =over 4 @@ -723,6 +855,22 @@ data debug +=item * + +add_drop_table + +=item * + +no_comments + +=item * + +trace + +=item * + +validate + =back All options are, well, optional; these attributes can be set via @@ -731,39 +879,31 @@ advantage is gained by passing options to the constructor. =head1 METHODS -=head2 B +=head2 add_drop_table Toggles whether or not to add "DROP TABLE" statements just before the create definitions. -=head2 B - -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. - -=head2 B +=head2 no_comments Toggles whether to print comments in the output. Accepts a true or false value, returns the current value. -=head2 B +=head2 producer -The B method is an accessor/mutator, used to retrieve or +The C 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) and passed 2 parameters: its container C instance and a data structure. It is expected that the function transform the data structure to a string. The C instance is provided for informational purposes; for example, the type of the parser can be -retrieved using the B method, and the B and -B methods can be called when needed. +retrieved using the C method, and the C and +C methods can be called when needed. When defining a producer, one of several things can be passed in: A -module name (e.g., C, a module name relative to -the C namespace (e.g., MySQL), a module +module name (e.g., C), a module name relative to +the C namespace (e.g., C), a module name and function combination (C), or a reference to an anonymous subroutine. If a full module name is passed in (for the purposes of this method, a string containing "::" @@ -772,8 +912,8 @@ 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, C will attempt -to load F and use transmogrify as the name of -the function, instead of the default "produce". +to load F and use C as the name of +the function, instead of the default C. my $tr = SQL::Translator->new; @@ -792,12 +932,12 @@ the function, instead of the default "produce". # $subref->($tr, $data); $tr->producer(\&my_producer); -There is also a method named B, which is a string -containing the classname to which the above B function +There is also a method named C, which is a string +containing the classname to which the above C function belongs. In the case of anonymous subroutines, this method returns the string "CODE". -Finally, there is a method named B, which is both an +Finally, there is a method named C, which is both an accessor and a mutator. Arbitrary data may be stored in name => value pairs for the producer subroutine to access: @@ -807,8 +947,8 @@ pairs for the producer subroutine to access: # $pr_args is a hashref. -Extra data passed to the B method is passed to -B: +Extra data passed to the C method is passed to +C: $tr->producer("xSV", delimiter => ',\s*'); @@ -816,11 +956,11 @@ B: my $args = $tr->producer_args; my $delimiter = $args->{'delimiter'}; # value is ,\s* -=head2 B +=head2 parser -The B method defines or retrieves a subroutine that will be +The C method defines or retrieves a subroutine that will be called to perform the parsing. The basic idea is the same as that of -B (see above), except the default subroutine name is +C (see above), except the default subroutine name is "parse", and will be invoked as C<$module_name::parse($tr, $data)>. Also, the parser subroutine will be passed a string containing the entirety of the data to be parsed. @@ -838,10 +978,10 @@ entirety of the data to be parsed. return $dumper->Dump; }); -There is also B and B, which perform -analogously to B and B +There is also C and C, which perform +analogously to C and C -=head2 B +=head2 show_warnings Toggles whether to print warnings of name conflicts, identifier mutations, etc. Probably only generated by producers to let the user @@ -849,15 +989,15 @@ 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 B +=head2 translate -The B method calls the subroutines referenced by the -B and B data members (described above). It accepts +The C method calls the subroutines referenced by the +C and C 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 and B methods). +C and C methods). -Here is how the parameter list to B is parsed: +Here is how the parameter list to C is parsed: =over @@ -895,12 +1035,12 @@ You get the idea. =back -=head2 B, B +=head2 filename, data -Using the B method, the filename of the data to be parsed -can be set. This method can be used in conjunction with the B -method, below. If both the B and B methods are -invoked as mutators, the data set in the B method is used. +Using the C method, the filename of the data to be parsed +can be set. This method can be used in conjunction with the C +method, below. If both the C and C methods are +invoked as mutators, the data set in the C method is used. $tr->filename("/my/data/files/create.sql"); @@ -913,26 +1053,67 @@ or: }; $tr->data(\$create_script); -B takes a string, which is interpreted as a filename. -B takes a reference to a string, which is used as the data to be +C takes a string, which is interpreted as a filename. +C 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 method is called, as long as the data instance +the C method is called, as long as the data instance variable is not set. -=pod +=head2 schema + +Returns the SQL::Translator::Schema object. -=head2 B +=head2 trace Turns on/off the tracing option of Parse::RecDescent. -=pod +=head2 validate + +Whether or not to validate the schema object after parsing and before +producing. =head1 AUTHORS -Ken Y. Clark, Ekclark@cpan.orgE, -darren chamberlain Edarren@cpan.orgE, -Chris Mungall Ecjm@fruitfly.orgE, -Allen Day Eallenday@users.sourceforge.netE +The following people have contributed to the SQLFairy project: + +=over 4 + +=item * Mark Addison + +=item * Sam Angiuoli + +=item * Darren Chamberlain + +=item * Ken Y. Clark + +=item * Allen Day + +=item * Paul Harrington + +=item * Mikey Melillo + +=item * Chris Mungall + +=item * Ross Smith II + +=item * Gudmundur A. Thorisson + +=item * Chris To + +=item * Jason Williams + +=item * Ying Zhang + +=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 @@ -952,12 +1133,21 @@ USA =head1 BUGS -Please use http://rt.cpan.org/ for reporting bugs. +Please use L for reporting bugs. + +=head1 PRAISE + +If you find this module useful, please use +L to rate it. =head1 SEE ALSO L, L, L, -L - +L, +L, +L, +L, +L, +L.