Changeset 32529 for main/trunk


Ignore:
Timestamp:
2018-10-19T20:42:08+13:00 (6 years ago)
Author:
ak19
Message:

Split the database functions into their own file gssql.pm, so that GreenstoneSQLPlugin can share some db releated code used by GreenstoneSQLPlugout.

Location:
main/trunk/greenstone2/perllib
Files:
1 added
1 edited

Legend:

Unmodified
Added
Removed

  • main/trunk/greenstone2/perllib/plugouts/GreenstoneSQLPlugout.pm

    r32527 r32529  
    3232no strict 'subs';
    3333
    34 use util;
    35 use FileUtils;
    3634use GreenstoneXMLPlugout;
    3735use docprint;
     36use gssql;
    3837
    3938use DBI; # the central package for this plugout
    4039
    41 use IPC::Open2;
    42 use POSIX ":sys_wait_h"; # for waitpid, http://perldoc.perl.org/functions/waitpid.html
    43 
    4440
    4541# TODO: SIGTERM rollback and disconnect?
    46 
    47 # TODO: rename class to GreenstoneSQLPlugout
    4842
    4943
    … …  
    5347}
    5448
     49# NOTTODO: die() statements need to be replaced with premature_termination
     50# which should ensure the GreenstoneXMLPlugin (group)'s stuff is closed and cleaned up SOMEHOW
     51# It's fine: the die() stmts all take place before setting up the super class' begin
    5552
    5653# TODO: deal with -removeold and everything? Or type out instructions for user
    … …  
    118115    ############ LOAD NECESSARY OPTIONS ###########
    119116    print STDERR "########## COLLECTION: ". $ENV{'GSDLCOLLECTION'}."\n";
    120     $self->{'collection_name'} = $ENV{'GSDLCOLLECTION'};
     117    #$self->{'collection_name'} = $ENV{'GSDLCOLLECTION'};
    121118    print STDERR "***** GreenstoneSQLPlugout process mode = \"", $self->{'process_mode'}, "\"\n";
    122    
    123     if(!$self->connect_to_db()) {
     119
     120    my $db_params = {
     121    'collection_name' => $ENV{'GSDLCOLLECTION'},
     122    'db_driver' => $self->{'db_driver'},
     123    'db_client_user' => $self->{'db_client_user'},
     124    'db_client_pwd' => $self->{'db_client_pwd'},
     125    'db_host' => $self->{'db_host'},
     126    'db_encoding' => $self->{'db_encoding'}
     127    #'db_name' => $self->{'site_name'},
     128    #'build_mode' => $self->{'build_mode'},
     129    };
     130
     131    my $gs_sql = new gssql($db_params);
     132   
     133    if(!$gs_sql->connect_to_db()) {
    124134    # This is fatal for the plugout, let's terminate here
    125135    # PrintError would already have displayed the warning message on connection fail   
    … …  
    129139    my $db_name = $self->{'site_name'} || "localsite"; # one database per GS3 site
    130140    my $build_mode = $self->{'build_mode'} || "removeold";
    131     if(!$self->load_db_and_tables($db_name, $build_mode)) {
     141    if(!$gs_sql->load_db_and_tables($db_name, $build_mode)) {
    132142   
    133143    # This is fatal for the plugout, let's terminate here
    … …  
    140150    my $proc_mode = $self->{'process_mode'};
    141151    if($proc_mode eq "all" || $proc_mode eq "meta_only" ) {
    142     $self->{'metadata_prepared_insert_statement_handle'} = $self->prepare_insert_metadata_row_stmthandle();
     152    $self->{'metadata_prepared_insert_statement_handle'} = $gs_sql->prepare_insert_metadata_row_stmthandle();
    143153    }
    144154    if($proc_mode eq "all" || $proc_mode eq "text_only" ) {
    145     $self->{'fulltxt_prepared_insert_statement_handle'} = $self->prepare_insert_fulltxt_row_stmthandle();
    146     }
    147 
     155    $self->{'fulltxt_prepared_insert_statement_handle'} = $gs_sql->prepare_insert_fulltxt_row_stmthandle();
     156    }
     157
     158    # store the DBI wrapper instance
     159    $self->{'gs_sql'} = $gs_sql;
     160   
    148161    print STDERR "#### Meta stmt: " . $self->{'metadata_prepared_insert_statement_handle'}->{'Statement'} . "\n";
    149162    print STDERR "#### Full stmt: " . $self->{'fulltxt_prepared_insert_statement_handle'}->{'Statement'} . "\n";
    … …  
    164177    $self->SUPER::end(@_);   
    165178   
    166     $self->disconnect_from_db() || warn("Unable to disconnect from database " . $self->{'site_name'} . "\n"); # disconnect_from_db() will also issue a warning, but this may be clearer
     179    $self->{'gs_sql'}->disconnect_from_db() || warn("Unable to disconnect from database " . $self->{'site_name'} . "\n"); # disconnect_from_db() will also issue a warning, but this may be clearer
    167180}
    168181 
    … …  
    304317}
    305318
    306 #################################
    307 
    308 # Database access related functions
    309 # http://g2pc1.bu.edu/~qzpeng/manual/MySQL%20Commands.htm
    310 # https://www.guru99.com/insert-into.html
    311 
    312 # TODO Q: What on cancelling a build: delete table? But what if it was a rebuild and the rebuild is cancelled (not the original build)?
    313 # Do we create a copy of the orig database as backup, then start populating current db, and if cancelled, delete current db and RENAME backup table to current?
    314 # https://stackoverflow.com/questions/3280006/duplicating-a-mysql-table-indexes-and-data
    315 # BUT what if the table is HUGE? (Think of a collection with millions of docs.) Huge overhead in copying?
    316 # The alternative is we just quit on cancel, but then: cancel could leave the table in a partial committed state, with no way of rolling back.
    317 # Unless they do a full rebuild, which will recreate the table from scratch?
    318 # SOLUTION-> rollback transaction on error, see https://www.effectiveperlprogramming.com/2010/07/set-custom-dbi-error-handlers/
    319 # But then should set AutoCommit to off on connection, and remember to commit every time
    320 
    321 #################
    322 # Database functions that use the perl DBI module (with the DBD driver module for mysql)
    323 #################
    324 
    325 # THE NEW DB FUNCTIONS
    326 # NOTE: FULLTEXT is a reserved keyword in (My)SQL. So we can't name a table or any of its columns "fulltext".
    327 # https://dev.mysql.com/doc/refman/5.5/en/keywords.html
    328 
    329 # TODO: Consider AutoCommit status (and Autocommit off allowing commit or rollback for GS coll build cancel) later
    330 
    331 sub connect_to_db {
    332     my $self= shift (@_);
    333    
    334     my $db_driver = $self->{'db_driver'};
    335     my $db_user = $self->{'db_client_user'} || "root";
    336     my $db_pwd = $self->{'db_client_pwd'};
    337     my $db_host = $self->{'db_host'} || "127.0.0.1";
    338     my $db_enc = $self->{'db_encoding'} || "utf8";
    339    
    340     #my $db_name = $self->{'site_name'};
    341    
    342     # try connecting to the mysql db, if that fails it will die
    343     # so don't bother preparing GreenstoneXMLPlugout by calling superclass' begin()
    344 
    345     # localhost doesn't work for us, but 127.0.0.1 works
    346     # https://metacpan.org/pod/DBD::mysql
    347     # "The hostname, if not specified or specified as '' or 'localhost', will default to a MySQL server
    348     # running on the local machine using the default for the UNIX socket. To connect to a MySQL server
    349     # on the local machine via TCP, you must specify the loopback IP address (127.0.0.1) as the host."
    350     #my $connect_str = "dbi:$db_driver:database=$db_name;host=$db_host";
    351     my $connect_str = "dbi:$db_driver:host=$db_host"; # don't provide db, so we can check the db is there
    352     my $dbh = DBI->connect("$connect_str", $db_user, $db_pwd,
    353                {
    354                    ShowErrorStatement => 1, # more informative as DBI will append failed SQL stmt to error message
    355                    PrintError => 1, # on by default, but being explicit
    356                    RaiseError => 0, # off by default, but being explicit
    357                    AutoCommit => 1 # on by default, but being explicit
    358                });
    359 
    360     if(!$dbh) {
    361     # NOTE, despite handle dbh being undefined, error code will be in DBI->err
    362     return 0;   
    363     }
    364 
    365     # set encoding https://metacpan.org/pod/DBD::mysql
    366     # https://dev.mysql.com/doc/refman/5.7/en/charset.html
    367     # https://dev.mysql.com/doc/refman/5.7/en/charset-conversion.html
    368     # Setting the encoding at db server level.
    369     # Not sure if this command is mysql specific:
    370     my $stmt = "set NAMES '" . $db_enc . "'";
    371     $dbh->do($stmt) || warn("Unable to set charset encoding at db server level to: " . $db_enc . "\n");
    372    
    373     # if we're here, then connection succeeded, store handle
    374     $self->{'db_handle'} = $dbh;
    375     return 1;
    376 }
    377 
    378 sub load_db_and_tables {
    379     my $self= shift (@_);
    380     my ($db_name, $build_mode) = @_;
    381     my $dbh = $self->{'db_handle'};
    382    
    383     # perl DBI switch database: https://www.perlmonks.org/?node_id=995434
    384     # do() returns undef on error.
    385     # connection succeeded, try to load our database. If that didn't work, attempt to create db
    386     my $success = $dbh->do("use $db_name");
    387    
    388     if(!$success && $dbh->err == 1049) { # "Unknown database" error has code 1049 (mysql only?) meaning db doesn't exist yet
    389     # attempt to create the db and its tables
    390     $self->create_db($db_name) || return 0;
    391 
    392     print STDERR "@@@ CREATED DATABASE $db_name\n";
    393    
    394     # once more attempt to use db, now that it exists
    395     $dbh->do("use $db_name") || return 0;
    396     #$dbh->do("use localsite") or die "Error (code" . $dbh->err ."): " . $dbh->errstr . "\n";
    397 
    398     # attempt to create tables in current db
    399     $self->create_metadata_table() || return 0;
    400     $self->create_fulltext_table() || return 0;
    401 
    402     $success = 1;
    403     }
    404     elsif($success) { # database existed and loaded successfully, but
    405     # before proceeding check that the current collection's tables exist
    406 
    407     print STDERR "@@@ DATABASE $db_name EXISTED\n";
    408    
    409 
    410     if($build_mode eq "removeold") {
    411         $self->delete_collection_tables();
    412     }
    413 
    414     # use existing tables if any
    415     # attempt to create tables in current db   
    416     if($build_mode eq "removeold" || !$self->table_exists($self->get_metadata_table_name())) {
    417         $self->create_metadata_table() || return 0;
    418     } else {
    419         print STDERR "@@@ Meta table exists\n";
    420     }
    421     if($build_mode eq "removeold" || !$self->table_exists($self->get_fulltext_table_name())) {
    422         $self->create_fulltext_table() || return 0;
    423     } else {
    424         print STDERR "@@@ Fulltxt table exists\n";
    425     }
    426    
    427     }
    428    
    429     return $success; # could still return 0, if database failed to load with an error code != 1049
    430 }
    431 
    432 # disconnect from db - https://metacpan.org/pod/DBI#disconnect
    433 # TODO: make sure to have committed or rolled back before disconnect
    434 # and that you've call finish() on statement handles if any fetch remnants remain
    435 sub disconnect_from_db {
    436     my $self= shift (@_);   
    437     my $dbh = $self->{'db_handle'};
    438 
    439     # make sure any active stmt handles are finished
    440     # NO: "When all the data has been fetched from a SELECT statement, the driver will automatically call finish for you. So you should not call it explicitly except when you know that you've not fetched all the data from a statement handle and the handle won't be destroyed soon."
    441    
    442     #$meta_sth = $self->{'metadata_prepared_insert_statement_handle'};
    443     #$txt_sth = $self->{'fulltxt_prepared_insert_statement_handle'};
    444     #$meta_sth->finish() if($meta_sth);
    445     #$txt_sth->finish() if($txt_sth);
    446    
    447     my $rc = $dbh->disconnect or warn $dbh->errstr; # The handle is of little use after disconnecting. Possibly PrintError already prints a warning and this duplicates it?
    448     return $rc;
    449 }
    450 
    451 sub create_db {
    452     my $self= shift (@_);
    453     my $db_name = $self->{'site_name'};
    454     my $dbh = $self->{'db_handle'};
    455    
    456     # https://stackoverflow.com/questions/5025768/how-can-i-create-a-mysql-database-from-a-perl-script
    457     return $dbh->do("create database $db_name"); # do() will return undef on fail, https://metacpan.org/pod/DBI#do
    458 }
    459 
    460 
    461 sub create_metadata_table {
    462     my $self= shift (@_);
    463     my $dbh = $self->{'db_handle'};
    464    
    465     my $table_name = $self->get_metadata_table_name();
    466 
    467     # If using an auto incremented primary key:
    468     my $stmt = "CREATE TABLE $table_name (id INT NOT NULL AUTO_INCREMENT, did VARCHAR(63) NOT NULL, sid VARCHAR(63) NOT NULL, metaname VARCHAR(127) NOT NULL, metavalue VARCHAR(1023) NOT NULL, PRIMARY KEY(id));";
    469     return $dbh->do($stmt);
    470 }
    471 
    472 # TODO: Investigate: https://dev.mysql.com/doc/search/?d=10&p=1&q=FULLTEXT
    473 # 12.9.1 Natural Language Full-Text Searches
    474 # to see whether we have to index the 'fulltxt' column of the 'fulltext' tables
    475 # or let user edit this file, or add it as another option
    476 sub create_fulltext_table {
    477     my $self= shift (@_);
    478     my $dbh = $self->{'db_handle'};
    479    
    480     my $table_name = $self->get_fulltext_table_name();
    481 
    482     # If using an auto incremented primary key:
    483     my $stmt = "CREATE TABLE $table_name (id INT NOT NULL AUTO_INCREMENT, did VARCHAR(63) NOT NULL, sid VARCHAR(63) NOT NULL, fulltxt LONGTEXT, PRIMARY KEY(id));";
    484     return $dbh->do($stmt);
    485 
    486 }
    487 
    488 
    489 # USEFUL: https://metacpan.org/pod/DBI
    490 # "Many methods have an optional \%attr parameter which can be used to pass information to the driver implementing the method. Except where specifically documented, the \%attr parameter can only be used to pass driver specific hints. In general, you can ignore \%attr parameters or pass it as undef."
    491 
    492 
    493 # https://www.guru99.com/insert-into.html
    494 # and https://dev.mysql.com/doc/refman/8.0/en/example-auto-increment.html
    495 #     for inserting multiple rows at once
    496 # https://www.perlmonks.org/bare/?node_id=316183
    497 # https://metacpan.org/pod/DBI#do
    498 # https://www.quora.com/What-is-the-difference-between-prepare-and-do-statements-in-Perl-while-we-make-a-connection-to-the-database-for-executing-the-query
    499 # https://docstore.mik.ua/orelly/linux/dbi/ch05_05.htm
    500 
    501 # https://metacpan.org/pod/DBI#performance
    502 # 'The q{...} style quoting used in this example avoids clashing with quotes that may be used in the SQL statement. Use the double-quote like qq{...} operator if you want to interpolate variables into the string. See "Quote and Quote-like Operators" in perlop for more details.'
    503 sub prepare_insert_metadata_row_stmthandle {
    504     my $self = shift (@_);   
    505     #my ($did, $sid, $metaname, $metavalue) = @_;
    506     my $dbh = $self->{'db_handle'};
    507    
    508     my $tablename = $self->get_metadata_table_name();
    509 
    510     #my $stmt = "INSERT INTO $tablename (did, sid, metaname, metavalue) VALUES ('$did', '$sid', '$metaname', '$metavalue');"; # ?, ?, ?, ?
    511 
    512     # using qq{} since we want $tablename placeholder to be filled in
    513     # returns Statement Handle object!
    514     my $sth = $dbh->prepare(qq{INSERT INTO $tablename (did, sid, metaname, metavalue) VALUES (?, ?, ?, ?)}) || warn("Could not prepare insert statement for metadata table\n");
    515 
    516     print STDERR "@@@@ Prepared meta insert statement: ".$sth->{'Statement'}."\n";
    517    
    518     return $sth;
    519 }
    520 
    521 sub prepare_insert_fulltxt_row_stmthandle {
    522     my $self = shift (@_);
    523     #my ($did, $sid, $fulltext) = @_;
    524     my $dbh = $self->{'db_handle'};
    525    
    526     my $tablename = $self->get_fulltext_table_name();
    527 
    528     #my $stmt = "INSERT INTO $tablename (did, sid, fulltxt) VALUES ('$did', '$sid', '$fulltext');"; ?, ?, ?
    529 
    530     # using qq{} since we want $tablename placeholder to be filled in
    531     # returns Statement Handle object!
    532     my $sth = $dbh->prepare(qq{INSERT INTO $tablename (did, sid, fulltxt) VALUES (?, ?, ?)}) || warn("Could not prepare insert statement for fulltxt table\n");
    533    
    534     print STDERR "@@@@ Prepared fulltext insert statement: ".$sth->{'Statement'}."\n";
    535    
    536     return $sth;
    537 }
    538 
    539 # "IF EXISTS is used to prevent an error from occurring if the database does not exist. ... DROP DATABASE returns the number of tables that were removed. The DROP DATABASE statement removes from the given database directory those files and directories that MySQL itself may create during normal operation.Jun 20, 2012"
    540 #MySQL 8.0 Reference Manual :: 13.1.22 DROP DATABASE Syntax
    541 # https://dev.mysql.com/doc/en/drop-database.html
    542 sub delete_collection_tables {
    543     my $self= shift (@_);
    544     my $dbh = $self->{'db_handle'};
    545    
    546     print STDERR "### Build mode is removeold, so deleting tables for current collection\n";
    547    
    548     # drop table <tablename>
    549     my $table = $self->get_metadata_table_name();
    550     $dbh->do("drop table $table") || warn("@@@ Couldn't delete $table");
    551     $table = $self->get_fulltext_table_name();
    552     $dbh->do("drop table $table") || warn("@@@ Couldn't delete $table");
    553 }
    554 
    555 # Don't call this: it will delete the meta and full text tables for ALL collections in $db_name (localsite by default)!
    556 # this is just for debugging
    557 sub _delete_database {
    558     my $self= shift (@_);
    559     my ($db_name) = @_;
    560     my $dbh = $self->{'db_handle'};
    561    
    562     # "drop database dbname"
    563     $dbh->do("drop database $db_name") || return 0;
    564 
    565     return 1;
    566 }
    567 
    568 # More basic helper methods
    569 sub get_metadata_table_name {
    570     my $self= shift (@_);
    571     my $table_name = $self->{'collection_name'} . "_metadata";
    572     return $table_name;
    573 }
    574 
    575 # FULLTEXT is a reserved keyword in (My)SQL. https://dev.mysql.com/doc/refman/5.5/en/keywords.html
    576 # So we can't name a table or any of its columns "fulltext". We use "fulltxt" instead.
    577 sub get_fulltext_table_name {
    578     my $self= shift (@_);
    579     my $table_name = $self->{'collection_name'} . "_fulltxt";
    580     return $table_name;
    581 }
    582 
    583 # I can get my version of table_exists to work, but it's not so ideal
    584 # Interesting that MySQL has non-standard command to CREATE TABLE IF NOT EXISTS and DROP TABLE IF EXISTS,
    585 # see https://www.perlmonks.org/bare/?node=DBI%20Recipes
    586 #    The page further has a table_exists function that could work with proper comparison
    587 # Couldn't get the first solution at https://www.perlmonks.org/bare/?node_id=500050 to work though
    588 sub table_exists {
    589     my $self = shift (@_);
    590     my $dbh = $self->{'db_handle'};
    591     my ($table_name) = @_;
    592 
    593     my @table_list = $dbh->tables;
    594     #my $tables_str = @table_list[0];
    595     foreach my $table (@table_list) {
    596     return 1 if ($table =~ m/$table_name/);
    597     }
    598     return 0;
    599 }
    600319
    6013201;
Note: See TracChangeset for help on using the changeset viewer.