AcePerl
view release on metacpan or search on metacpan
# Items to export into callers namespace by default.
@EXPORT = qw(STATUS_WAITING STATUS_PENDING STATUS_ERROR);
# Optional exports
@EXPORT_OK = qw(rearrange ACE_PARSE);
$VERSION = '1.92';
use constant STATUS_WAITING => 0;
use constant STATUS_PENDING => 1;
use constant STATUS_ERROR => -1;
use constant ACE_PARSE => 3;
use constant DEFAULT_PORT => 200005; # rpc server
use constant DEFAULT_SOCKET => 2005; # socket server
require Ace::Iterator;
require Ace::Object;
eval qq{use Ace::Freesubs}; # XS file, may not be available
# Map database names to objects (to fix file-caching issue)
my %NAME2DB;
# internal cache of objects
my %MEMORY_CACHE;
my %DEFAULT_CACHE_PARAMETERS = (
default_expires_in => '1 day',
auto_purge_interval => '12 hours',
);
# Preloaded methods go here.
$Error = '';
# Pseudonyms and deprecated methods.
*list = \&fetch;
*Ace::ERR = *Error;
# now completely deprecated and gone
# *find_many = \&fetch_many;
# *models = \&classes;
sub connect {
my $class = shift;
my ($host,$port,$user,$pass,$path,$program,
$objclass,$timeout,$query_timeout,$database,
$server_type,$url,$u,$p,$cache,$other);
# one-argument single "URL" form
if (@_ == 1) {
return $class->connect(-url=>shift);
}
# multi-argument (traditional) form
($host,$port,$user,$pass,
$path,$objclass,$timeout,$query_timeout,$url,$cache,$other) =
rearrange(['HOST','PORT','USER','PASS',
'PATH',['CLASS','CLASSMAPPER'],'TIMEOUT',
'QUERY_TIMEOUT','URL','CACHE'],@_);
($host,$port,$u,$pass,$p,$server_type) = $class->process_url($url)
or croak "Usage: Ace->connect(-host=>\$host,-port=>\$port [,-path=>\$path]\n"
if defined $url;
if ($path) { # local database
$server_type = 'Ace::Local';
} else { # either RPC or socket server
$host ||= 'localhost';
$user ||= $u || '';
$path ||= $p || '';
$port ||= $server_type eq 'Ace::SocketServer' ? DEFAULT_SOCKET : DEFAULT_PORT;
$query_timeout = 120 unless defined $query_timeout;
$server_type ||= 'Ace::SocketServer' if $port < 100000;
$server_type ||= 'Ace::RPC' if $port >= 100000;
}
# we've normalized parameters, so do the actual connect
eval "require $server_type" || croak "Module $server_type not loaded: $@";
if ($path) {
$database = $server_type->connect(-path=>$path,%$other);
} else {
$database = $server_type->connect($host,$port,$query_timeout,$user,$pass,%$other);
}
unless ($database) {
$Ace::Error ||= "Couldn't open database";
return;
}
my $contents = {
'database'=> $database,
'host' => $host,
'port' => $port,
'path' => $path,
'class' => $objclass || 'Ace::Object',
'timeout' => $query_timeout,
'user' => $user,
'pass' => $pass,
'other' => $other,
'date_style' => 'java',
'auto_save' => 0,
};
my $self = bless $contents,ref($class)||$class;
$self->_create_cache($cache) if $cache;
$self->name2db("$self",$self);
return $self;
}
sub reopen {
my $self = shift;
return 1 if $self->ping;
my $class = ref($self->{database});
my $database;
if ($self->{path}) {
$database = $class->connect(-path=>$self->{path},%{$self->other});
} else {
$database = $class->connect($self->{host},$self->{port}, $self->{timeout},
$self->{user},$self->{pass},%{$self->{other}});
}
unless ($database) {
$Ace::Error = "Couldn't open database";
return;
}
$self->{database} = $database;
1;
}
sub class {
my $self = shift;
my $d = $self->{class};
$self->{class} = shift if @_;
$d;
}
sub class_for {
my $self = shift;
my ($class,$id) = @_;
my $selected_class;
if (my $selector = $self->class) {
if (ref $selector eq 'HASH') {
$selected_class = $selector->{$class} || $selector->{'_DEFAULT_'};
}
elsif ($selector->can('class_for')) {
$selected_class = $selector->class_for($class,$id,$self);
}
elsif (!ref $selector) {
$selected_class = $selector;
}
else {
croak "$selector is neither a scalar, nor a HASH, nor an object that supports the class_for() method";
}
}
$selected_class ||= 'Ace::Object';
eval "require $selected_class; 1;" || croak $@
unless $selected_class->can('new');
$selected_class;
}
sub process_url {
my $class = shift;
my $url = shift;
my ($host,$port,$user,$pass,$path,$server_type) = ('','','','','','');
if ($url) { # look for host:port
local $_ = $url;
if (m!^rpcace://([^:]+):(\d+)$!) { # rpcace://localhost:200005
($host,$port) = ($1,$2);
$server_type = 'Ace::RPC';
} elsif (m!^sace://([\w:]+)\@([^:]+):(\d+)$!) { # sace://user@localhost:2005
($user,$host,$port) = ($1,$2,$3);
$server_type = 'Ace::SocketServer';
} elsif (m!^sace://([^:]+):(\d+)$!) { # sace://localhost:2005
($host,$port) = ($1,$2);
$server_type = 'Ace::SocketServer';
} elsif (m!^tace:(/.+)$!) { # tace:/path/to/database
$path = $1;
$server_type = 'Ace::Local';
} elsif (m!^(/.+)$!) { # /path/to/database
$path = $1;
$server_type = 'Ace::Local';
} else {
return;
}
}
if ($user =~ /:/) {
($user,$pass) = split /:/,$user;
}
return ($host,$port,$user,$pass,$path,$server_type);
}
# Return the low-level Ace::AceDB object
sub db {
return $_[0]->{'database'};
}
# Fetch a model from the database.
# Since there are limited numbers of models, we cache
# the results internally.
sub model {
my $self = shift;
require Ace::Model;
my $model = shift;
my $break_cycle = shift; # for breaking cycles when following #includes
my $key = join(':',$self,'MODEL',$model);
$self->{'models'}{$model} ||= eval{$self->cache->get($key)};
unless ($self->{models}{$model}) {
$self->{models}{$model} =
Ace::Model->new($self->raw_query("model \"$model\""),$self,$break_cycle);
eval {$self->cache->set($key=>$self->{models}{$model})};
}
return $self->{'models'}{$model};
}
# cached get
# pass "1" for fill to get a full fill
# pass any other true value to get a tag fill
argument.
=item B<-path>
This argument indicates the path of an AceDB directory on the local
system. It should point to the directory that contains the I<wspec>
subdirectory. User name interpolations (~acedb) are OK.
=item B<-user>
Name of user to log in as (when using socket server B<only>). If not
provided, will attempt an anonymous login.
=item B<-pass>
Password to log in with (when using socket server).
=item B<-url>
An Acedb URL that combines the server type, host, port, user and
password in a single string. See the connect() method's "single
argument form" description.
=item B<-cache>
AcePerl can use the Cache::SizeAwareFileCache module to cache objects
to disk. This can result in dramatically increased performance in
environments such as web servers in which the same Acedb objects are
frequently reused. To activate this mechanism, the
Cache::SizeAwareFileCache module must be installed, and you must pass
the -cache argument during the connect() call.
The value of -cache is a hash reference containing the arguments to be
passed to Cache::SizeAwareFileCache. For example:
-cache => {
cache_root => '/usr/tmp/acedb',
cache_depth => 4,
default_expires_in => '1 hour'
}
If not otherwise specified, the following cache parameters are assumed:
Parameter Default Value
--------- -------------
namespace Server URL (e.g. sace://localhost:2005)
cache_root /tmp/FileCache (dependent on system temp directory)
default_expires_in 1 day
auto_purge_interval 12 hours
By default, the cache is not size limited (the "max_size" property is
set to $NO_MAX_SIZE). To adjust the size you may consider calling the
Ace object's cache() method to retrieve the physical cache and then
calling the cache object's limit_size($max_size) method from time to
time. See L<Cache::SizeAwareFileCache> for more details.
=item B<-program>
By default AcePerl will use its internal compiled code calls to
establish a connection to Ace servers, and will launch a I<tace>
subprocess to communicate with local Ace databases. The B<-program>
argument allows you to customize this behavior by forcing AcePerl to
use a local program to communicate with the database. This argument
should point to an executable on your system. You may use either a
complete path or a bare command name, in which case the PATH
environment variable will be consulted. For example, you could force
AcePerl to use the I<aceclient> program to connect to the remote host
by connecting this way:
$db = Ace->connect(-host => 'beta.crbm.cnrs-mop.fr',
-port => 20000100,
-program=>'aceclient');
=item B<-classmapper>
The optional B<-classmapper> argument (alias B<-class>) points to the
class you would like to return from database queries. It is provided
for your use if you subclass Ace::Object. For example, if you have
created a subclass of Ace::Object called Ace::Object::Graphics, you
can have the database return this subclass by default by connecting
this way:
$db = Ace->connect(-host => 'beta.crbm.cnrs-mop.fr',
-port => 20000100,
-class=>'Ace::Object::Graphics');
The value of B<-class> can be a hash reference consisting of AceDB
class names as keys and Perl class names as values. If a class name
does not exist in the hash, a key named _DEFAULT_ will be looked for.
If that does not exist, then Ace will default to Ace::Object.
The value of B<-class> can also be an object or a classname that
implements a class_for() method. This method will receive three
arguments containing the AceDB class name, object ID and database
handle. It should return a string indicating the perl class to
create.
=item B<-timeout>
If no response from the server is received within $timeout seconds,
the call will return an undefined value. Internally timeout sets an
alarm and temporarily intercepts the ALRM signal. You should be aware
of this if you use ALRM for your own purposes.
NOTE: this feature is temporarily disabled (as of version 1.40)
because it is generating unpredictable results when used with
Apache/mod_perl.
=item B<-query_timeout>
If any query takes longer than $query_timeout seconds, will return an
undefined value. This value can only be set at connect time, and cannot
be changed once set.
=back
If arguments are omitted, they will default to the following values:
-host localhost
-port 200005;
-path no default
=head2 reopen() Method
The ACeDB socket server can time out. The reopen() method will ping
the server and if it is not answering will reopen the connection. If
the database is live (or could be resurrected), this method returns
true.
=head1 RETRIEVING ACEDB OBJECTS
Once you have established a connection and have an Ace databaes
handle, several methods can be used to query the ACE database to
retrieve objects. You can then explore the objects, retrieve specific
fields from them, or update them using the I<Ace::Object> methods.
Please see L<Ace::Object>.
=head2 fetch() method
$count = $db->fetch($class,$name_pattern);
$object = $db->fetch($class,$name);
@objects = $db->fetch($class,$name_pattern,[$count,$offset]);
@objects = $db->fetch(-name=>$name_pattern,
-class=>$class
-count=>$count,
-offset=>$offset,
-fill=>$fill,
-filltag=>$tag,
-total=>\$total);
@objects = $db->fetch(-query=>$query);
Ace::fetch() retrieves objects from the database based on their class
and name. You may retrieve a single object by requesting its name, or
a group of objects by fetching a name I<pattern>. A pattern contains
one or more wildcard characters, where "*" stands for zero or more
characters, and "?" stands for any single character.
This method behaves differently depending on whether it is called in a
scalar or a list context, and whether it is asked to search for a name
pattern or a simple name.
When called with a class and a simple name, it returns the object
referenced by that time, or undef, if no such object exists. In an
array context, it will return an empty list.
When called with a class and a name pattern in a list context, fetch()
returns the list of objects that match the name. When called with a
pattern in a scalar context, fetch() returns the I<number> of objects
that match without actually retrieving them from the database. Thus,
it is similar to count().
In the examples below, the first line of code will fetch the Sequence
object whose database ID is I<D12345>. The second line will retrieve
all objects matching the pattern I<D1234*>. The third line will
return the count of objects that match the same pattern.
$object = $db->fetch(Sequence => 'D12345');
@objects = $db->fetch(Sequence => 'D1234*');
$cnt = $db->fetch(Sequence =>'D1234*');
A variety of communications and database errors may occur while
processing the request. When this happens, undef or an empty list
will be returned, and a string describing the error can be retrieved
by calling Ace->error.
When retrieving database objects, it is possible to retrieve a
"filled" or an "unfilled" object. A filled object contains the entire
contents of the object, including all tags and subtags. In the case
of certain Sequence objects, this may be a significant amount of data.
Unfilled objects consist just of the object name. They are filled in
from the database a little bit at a time as tags are requested. By
default, fetch() returns the unfilled object. This is usually a
performance win, but if you know in advance that you will be needing
the full contents of the retrieved object (for example, to display
them in a tree browser) it can be more efficient to fetch them in
filled mode. You do this by calling fetch() with the argument of
B<-fill> set to a true value.
The B<-filltag> argument, if provided, asks the database to fill in
the subtree anchored at the indicated tag. This will improve
performance for frequently-accessed subtrees. For example:
@objects = $db->fetch(-name => 'D123*',
-class => 'Sequence',
-filltag => 'Visible');
This will fetch all Sequences named D123* and fill in their Visible
trees in a single operation.
Other arguments in the named parameter calling form are B<-count>, to
retrieve a certain maximum number of objects, and B<-offset>, to
retrieve objects beginning at the indicated offset into the list. If
you want to limit the number of objects returned, but wish to learn
how many objects might have been retrieved, pass a reference to a
scalar variable in the B<-total> argument. This will return the
object count. This example shows how to fetch 100 Sequence
objects, starting at Sequence number 500:
@some_sequences = $db->fetch('Sequence','*',100,500);
The next example uses the named argument form to fetch 100 Sequence
objects starting at Sequence number 500, and leave the total number of
Sequences in $total:
@some_sequences = $db->fetch(-class => 'Sequence',
-count => 100,
-offset => 500,
-total => \$total);
Notice that if you leave out the B<-name> argument the "*" wildcard is
assumed.
You may also pass an arbitrary Ace query string with the B<-query>
argument. This will supersede any name and class you provide.
Example:
@ready_dnas= $db->fetch(-query=>
'find Annotation Ready_for_submission ; follow gene ;
follow derived_sequence ; >DNA');
If your request is likely to retrieve very many objects, fetch() many
consume a lot of memory, even if B<-fill> is false. Consider using
B<fetch_many()> instead (see below). Also see the get() method, which
is equivalent to the simple two-argument form of fetch().
=item get() method
$object = $db->get($class,$name [,$fill]);
The get() method will return one and only one AceDB object
identified by its class and name. The optional $fill argument can be
used to control how much data is retrieved from the database. If $fill
is absent or undefined, then the method will return a lightweight
"stub" object that is filled with information as requested in a lazy
fashion. If $fill is the number "1" then the retrieved object contains
all the relevant information contained within the database. Any other
true value of $fill will be treated as a tag name: the returned object
will be prefilled with the subtree to the right of that tag.
Examples:
# return lightweight stub for Author object "Sulston JE."
$author = $db->get(Author=>'Sulston JE');
# return heavyweight object
$author = $db->get(Author=>'Sulston JE',1);
# return object containing the Address subtree
$author = $db->get(Author=>'Sulston JE','Address');
The get() method is equivalent to this form of the fetch()
method:
$object = $db->fetch($class=>$name);
=head2 aql() method
$count = $db->aql($aql_query);
@objects = $db->aql($aql_query);
Ace::aql() will perform an AQL query on the database. In a scalar
context it returns the number of rows returned. In an array context
it returns a list of rows. Each row is an anonymous array containing
the columns returned by the query as an Ace::Object.
If an AQL error is encountered, will return undef or an empty list and
set Ace->error to the error message.
Note that this routine is not optimized -- there is no iterator
defined. All results are returned synchronously, leading to large
memory consumption for certain queries.
=head2 put() method
$cnt = $db->put($obj1,$obj2,$obj3);
This method will put the list of objects into the database,
overwriting like-named objects if they are already there. This can
be used to copy an object from one database to another, provided that
the models are compatible.
The method returns the count of objects successfully written into the
database. In case of an error, processing will stop at the last
object successfully written and an error message will be placed in
Ace->error();
=head2 parse() method
$object = $db->parse('data to parse');
This will parse the Ace tags contained within the "data to parse"
string, convert it into an object in the databse, and return the
resulting Ace::Object. In case of a parse error, the undefined value
will be returned and a (hopefully informative) description of the
error will be returned by Ace->error().
For example:
$author = $db->parse(<<END);
Author : "Glimitz JR"
Full_name "Jonathan R. Glimitz"
Mail "128 Boylston Street"
Mail "Boston, MA"
Mail "USA"
Laboratory GM
END
This method can also be used to parse several objects, but only the
last object successfully parsed will be returned.
=head2 parse_longtext() method
$object = $db->parse($title,$text);
This will parse the long text (which may contain carriage returns and
other funny characters) and place it into the database with the given
title. In case of a parse error, the undefined value will be returned
and a (hopefully informative) description of the error will be
returned by Ace->error(); otherwise, a LongText object will be returned.
For example:
$author = $db->parse_longtext('A Novel Inhibitory Domain',<<END);
We have discovered a novel inhibitory domain that inhibits
many classes of proteases, including metallothioproteins.
This inhibitory domain appears in three different gene families studied
to date...
END
=head2 parse_file() method
@objects = $db->parse_file('/path/to/file');
@objects = $db->parse_file('/path/to/file',1);
This will call parse() to parse each of the objects found in the
indicated .ace file, returning the list of objects successfully loaded
into the database.
By default, parsing will stop at the first object that causes a parse
error. If you wish to forge on after an error, pass a true value as
the second argument to this method.
Any parse error messages are accumulated in Ace->error().
@objects = $db->keyset($keyset_name);
This method returns all objects in a named keyset. Wildcard
characters are accepted, in which case all keysets that match the
pattern will be retrieved and merged into a single list of unique
objects.
=head2 grep() method
@objects = $db->grep($grep_string);
$count = $db->grep($grep_string);
@objects = $db->grep(-pattern => $grep_string,
-offset=> $offset,
-count => $count,
-fill => $fill,
-filltag => $filltag,
-total => \$total,
-long => 1,
);
This performs a "grep" on the database, returning all object names or
text that contain the indicated grep pattern. In a scalar context
this call will return the number of matching objects. In an array
context, the list of matching objects are retrieved. There is also a
named-parameter form of the call, which allows you to specify the
number of objects to retrieve, the offset from the beginning of the
list to retrieve from, whether the retrieved objects should be filled
initially. You can use B<-total> to discover the total number of
objects that match, while only retrieving a portion of the list.
By default, grep uses a fast search that only examines class names and
lexiques. By providing a true value to the B<-long> parameter, you
can search inside LongText and other places that are not usually
touched on, at the expense of much more CPU time.
Due to "not listable" objects that may match during grep, the list of
objects one can retrieve may not always match the count.
=head2 model() method
$model = $db->model('Author');
This will return an I<Ace::Model> object corresponding to the
indicated class.
=head2 new() method
$obj = $db->new($class,$name);
$obj = $db->new(-class=>$class,
-name=>$name);
Create a new object in the database with the indicated class and name
and return a pointer to it. Will return undef if the object already
exists in the database. The object isn't actually written into the database
until you call Ace::Object::commit().
=head2 raw_query() method
$r = $db->raw_query('Model');
Send a command to the database and return its unprocessed output.
This method is necessary to gain access to features that are not yet
implemented in this module, such as model browsing and complex
queries.
=head2 classes() method
@classes = $db->classes();
@all_classes = $db->classes(1);
This method returns a list of all the object classes known to the
server. In a list context it returns an array of class names. In a
scalar context, it the number of classes defined in the database.
Ordinarily I<classes()> will return only those classes that are
exposed to the user interface for browsing, the so-called "visible"
classes. Pass a true argument to the call to retrieve non-visible
classes as well.
=head2 class_count() method
%classes = $db->class_count()
This returns a hash in which the keys are the class names and the
values are the total number of objects in that class. All classes
are returned, including invisible ones. Use this method if you need
to count all classes simultaneously. If you only want to count one
or two classes, it may be more efficient to call I<count($class_name)>
instead.
This method transiently uses a lot of memory. It should not be used
with Ace 4.5 servers, as they contain a memory leak in the counting
routine.
=head2 status() method
%status = $db->status;
$status = $db->status;
Returns various bits of status information from the server. In an
array context, returns a hash of hashes. In a scalar context, returns a
reference to a hash of hashes. Keys and subkeys are as follows
code
program name of acedb binary
version version of acedb binary
build build date of acedb binary in format Jan 25 2003 16:21:24
database
title name of the database
version version of the database
dbformat database format version number
directory directory in which the database is stored
session session number
user user under which server is running
write whether the server has write access
address global address - not known if this is useful
resources
classes number of classes defined
keys number of keys defined
( run in 1.412 second using v1.01-cache-2.11-cpan-995e09ba956 )