[Bio] / Sprout / ERDB.pm Repository:
ViewVC logotype

Diff of /Sprout/ERDB.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.72, Mon Oct 16 07:44:41 2006 UTC revision 1.73, Fri Nov 3 00:33:26 2006 UTC
# Line 11  Line 11 
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12      use Digest::MD5 qw(md5_base64);      use Digest::MD5 qw(md5_base64);
13      use FIG;      use FIG;
14        use CGI;
15    
16  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
17    
# Line 59  Line 60 
60  B<start-position>, which indicates where in the contig that the sequence begins. This attribute  B<start-position>, which indicates where in the contig that the sequence begins. This attribute
61  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.  is implemented as the C<start_position> field in the C<IsMadeUpOf> relation.
62    
63  The database itself is described by an XML file using the F<ERDatabase.xsd> schema. In addition to  The database itself is described by an XML file. In addition to all the data required to define
64  all the data required to define the entities, relationships, and attributes, the schema provides  the entities, relationships, and attributes, the schema provides space for notes describing
65  space for notes describing the data and what it means. These notes are used by L</ShowMetaData>  the data and what it means. These notes are used by L</ShowMetaData> to generate documentation
66  to generate documentation for the database.  for the database.
67    
68    Special support is provided for text searching. An entity field can be marked as <em>searchable</em>,
69    in which case it will be used to generate a text search index in which the user searches for words
70    in the field instead of a particular field value.
71    
72  Finally, every entity and relationship object has a flag indicating if it is new or old. The object  Finally, every entity and relationship object has a flag indicating if it is new or old. The object
73  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it  is considered I<old> if it was loaded by the L</LoadTables> method. It is considered I<new> if it
74  was inserted by the L</InsertObject> method.  was inserted by the L</InsertObject> method.
75    
 To facilitate testing, the ERDB module supports automatic generation of test data. This process  
 is described in the L</GenerateEntity> and L</GenerateConnection> methods, though it is not yet  
 fully implemented.  
   
76  =head2 XML Database Description  =head2 XML Database Description
77    
78  =head3 Data Types  =head3 Data Types
# Line 217  Line 218 
218  index will be created for each relation with at least one searchable field in it.  index will be created for each relation with at least one searchable field in it.
219  For best results, this option should only be used for string or text fields.  For best results, this option should only be used for string or text fields.
220    
221    =item special
222    
223    This attribute allows the subclass to assign special meaning for certain fields.
224    The interpretation is up to the subclass itself. Currently, only entity fields
225    can have this attribute.
226    
227  =back  =back
228    
229  =head3 Indexes  =head3 Indexes
# Line 328  Line 335 
335    
336  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
337  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
338  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "avgLen" is the average byte length for estimating
339  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # record sizes. "sort" is the key modifier for the sort command, "notes" is a type description.
340  # record sizes. "sort" is the key modifier for the sort command.  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",
341  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  dataGen => "StringGen('A')" },                                 notes => "single ASCII character"},
342                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n",
343                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },                                 notes => "signed 32-bit integer"},
344                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",  dataGen => "StringGen(IntGen(10,250))" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n",
345                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",  dataGen => "StringGen(IntGen(80,1000))" },                                 notes => "unsigned 32-bit integer"},
346                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n", dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",
347                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g", dataGen => "FloatGen(0.0, 100.0)" },                                 notes => "character string, 0 to 255 characters"},
348                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n", dataGen => "IntGen(0, 1)" },                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",
349                                   notes => "character string, nearly unlimited length, cannot be indexed"},
350                      date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n",
351                                   notes => "signed, 64-bit integer"},
352                      float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g",
353                                   notes => "64-bit double precision floating-point number"},
354                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n",
355                                   notes => "boolean value: 0 if false, 1 if true"},
356                   'hash-string' =>                   'hash-string' =>
357                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",  dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",
358                                   notes => "string stored in digested form, used for certain types of key fields"},
359                   'id-string' =>                   'id-string' =>
360                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",  dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",
361                                   notes => "character string, 0 to 25 characters"},
362                   'key-string' =>                   'key-string' =>
363                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",  dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",
364                                   notes => "character string, 0 to 40 characters"},
365                   'name-string' =>                   'name-string' =>
366                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",
367                                   notes => "character string, 0 to 80 characters"},
368                   'medium-string' =>                   'medium-string' =>
369                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",
370                                   notes => "character string, 0 to 160 characters"},
371                  );                  );
372    
373  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 357  Line 376 
376                     'MM' => 'many-to-many'                     'MM' => 'many-to-many'
377                   );                   );
378    
379  # Table for interpreting string patterns.  # Options for XML input and output.
380    
381  my %PictureTable = ( 'A' => "abcdefghijklmnopqrstuvwxyz",  my %XmlOptions = (GroupTags =>  { Relationships => 'Relationship',
382                       '9' => "0123456789",                                    Entities => 'Entity',
383                       'X' => "abcdefghijklmnopqrstuvwxyz0123456789",                                    Fields => 'Field',
384                       'V' => "aeiou",                                    Indexes => 'Index',
385                       'K' => "bcdfghjklmnoprstvwxyz"                                    IndexFields => 'IndexField'
386                                    },
387                      KeyAttr =>    { Relationship => 'name',
388                                      Entity => 'name',
389                                      Field => 'name'
390                                    },
391                      SuppressEmpty => 1,
392                     );                     );
393    
394    my %XmlInOpts  = (
395                      ForceArray => ['Field', 'Index', 'IndexField'],
396                      ForceContent => 1,
397                      NormalizeSpace => 2,
398                     );
399    my %XmlOutOpts = (
400                      RootName => 'Database',
401                      XMLDecl => 1,
402                     );
403    
404    
405  =head2 Public Methods  =head2 Public Methods
406    
407  =head3 new  =head3 new
# Line 506  Line 542 
542          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
543          # If there's descriptive text, display it.          # If there's descriptive text, display it.
544          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
545              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
546          }          }
547          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
548          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
# Line 563  Line 599 
599          $retVal .= "</p>\n";          $retVal .= "</p>\n";
600          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
601          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
602              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . HTMLNote($notes->{content}) . "</p>\n";
603          }          }
604          # Generate the relationship's relation table.          # Generate the relationship's relation table.
605          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
# Line 964  Line 1000 
1000      return sort keys %{$entityList};      return sort keys %{$entityList};
1001  }  }
1002    
1003    =head3 GetDataTypes
1004    
1005    C<< my %types = ERDB::GetDataTypes(); >>
1006    
1007    Return a table of ERDB data types. The table returned is a hash of hashes.
1008    The keys of the big hash are the datatypes. Each smaller hash has several
1009    values used to manage the data. The most interesting is the SQL type (key
1010    C<sqlType>) and the descriptive node (key C<notes>).
1011    
1012    Note that changing the values in the smaller hashes will seriously break
1013    things, so this data should be treated as read-only.
1014    
1015    =cut
1016    
1017    sub GetDataTypes {
1018        return %TypeTable;
1019    }
1020    
1021    
1022  =head3 IsEntity  =head3 IsEntity
1023    
1024  C<< my $flag = $erdb->IsEntity($entityName); >>  C<< my $flag = $erdb->IsEntity($entityName); >>
# Line 1253  Line 1308 
1308      return @retVal;      return @retVal;
1309  }  }
1310    
1311    =head3 SpecialFields
1312    
1313    C<< my %specials = $erdb->SpecialFields($entityName); >>
1314    
1315    Return a hash mapping special fields in the specified entity to the value of their
1316    C<special> attribute. This enables the subclass to get access to the special field
1317    attributes without needed to plumb the internal ERDB data structures.
1318    
1319    =over 4
1320    
1321    =item entityName
1322    
1323    Name of the entity whose special fields are desired.
1324    
1325    =item RETURN
1326    
1327    Returns a hash. The keys of the hash are the special field names, and the values
1328    are the values from each special field's C<special> attribute.
1329    
1330    =back
1331    
1332    =cut
1333    
1334    sub SpecialFields {
1335        # Get the parameters.
1336        my ($self, $entityName) = @_;
1337        # Declare the return variable.
1338        my %retVal = ();
1339        # Find the entity's data structure.
1340        my $entityData = $self->{Entities}->{$entityName};
1341        # Loop through its fields, adding each special field to the return hash.
1342        my $fieldHash = $entityData->{Fields};
1343        for my $fieldName (keys %{$fieldHash}) {
1344            my $fieldData = $fieldHash->{$fieldName};
1345            if (exists $fieldData->{special}) {
1346                $retVal{$fieldName} = $fieldData->{special};
1347            }
1348        }
1349        # Return the result.
1350        return %retVal;
1351    }
1352    
1353  =head3 Delete  =head3 Delete
1354    
1355  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID); >>
# Line 2023  Line 2120 
2120      };      };
2121      if (!defined $rv) {      if (!defined $rv) {
2122          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
2123          $retVal->AddMessage("Table load failed for $relationName using $fileName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName: " . $dbh->error_message);
2124          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
2125      } else {      } else {
2126          # Here we successfully loaded the table.          # Here we successfully loaded the table.
# Line 2068  Line 2165 
2165      return $retVal;      return $retVal;
2166  }  }
2167    
2168  =head3 GenerateEntity  =head3 DropRelation
2169    
2170  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>  C<< $erdb->DropRelation($relationName); >>
2171    
2172  Generate the data for a new entity instance. This method creates a field hash suitable for  Physically drop a relation from the database.
 passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  
 of the fields are generated using information in the database schema.  
   
 Each data type has a default algorithm for generating random test data. This can be overridden  
 by including a B<DataGen> element in the field. If this happens, the content of the element is  
 executed as a PERL program in the context of this module. The element may make use of a C<$this>  
 variable which contains the field hash as it has been built up to the current point. If any  
 fields are dependent on other fields, the C<pass> attribute can be used to control the order  
 in which the fields are generated. A field with a high data pass number will be generated after  
 a field with a lower one. If any external values are needed, they should be passed in via the  
 optional third parameter, which will be available to the data generation script under the name  
 C<$value>. Several useful utility methods are provided for generating random values, including  
 L</IntGen>, L</StringGen>, L</FloatGen>, and L</DateGen>. Note that dates are stored and generated  
 in the form of a timestamp number rather than a string.  
2173    
2174  =over 4  =over 4
2175    
2176  =item id  =item relationName
   
 ID to assign to the new entity.  
   
 =item type  
   
 Type name for the new entity.  
   
 =item values  
2177    
2178  Hash containing additional values that might be needed by the data generation methods (optional).  Name of the relation to drop. If it does not exist, this method will have
2179    no effect.
2180    
2181  =back  =back
2182    
2183  =cut  =cut
2184    
2185  sub GenerateEntity {  sub DropRelation {
2186      # Get the parameters.      # Get the parameters.
2187      my ($self, $id, $type, $values) = @_;      my ($self, $relationName) = @_;
2188      # Create the return hash.      # Get the database handle.
2189      my $this = { id => $id };      my $dbh = $self->{_dbh};
2190      # Get the metadata structure.      # Drop the relation. The method used here has no effect if the relation
2191      my $metadata = $self->{_metaData};      # does not exist.
2192      # Get this entity's list of fields.      $dbh->drop_table($relationName);
     if (!exists $metadata->{Entities}->{$type}) {  
         Confess("Unrecognized entity type $type in GenerateEntity.");  
     } else {  
         my $entity = $metadata->{Entities}->{$type};  
         my $fields = $entity->{Fields};  
         # Generate data from the fields.  
         _GenerateFields($this, $fields, $type, $values);  
     }  
     # Return the hash created.  
     return $this;  
2193  }  }
2194    
2195  =head3 GetEntity  =head3 GetEntity
# Line 2457  Line 2523 
2523      return $objectData->{Fields};      return $objectData->{Fields};
2524  }  }
2525    
2526    =head3 SplitKeywords
2527    
2528    C<< my @keywords = ERDB::SplitKeywords($keywordString); >>
2529    
2530    This method returns a list of the positive keywords in the specified
2531    keyword string. All of the operators will have been stripped off,
2532    and if the keyword is preceded by a minus operator (C<->), it will
2533    not be in the list returned. The idea here is to get a list of the
2534    keywords the user wants to see. The list will be processed to remove
2535    duplicates.
2536    
2537    It is possible to create a string that confuses this method. For example
2538    
2539        frog toad -frog
2540    
2541    would return both C<frog> and C<toad>. If this is a problem we can deal
2542    with it later.
2543    
2544    =over 4
2545    
2546    =item keywordString
2547    
2548    The keyword string to be parsed.
2549    
2550    =item RETURN
2551    
2552    Returns a list of the words in the keyword string the user wants to
2553    see.
2554    
2555    =back
2556    
2557    =cut
2558    
2559    sub SplitKeywords {
2560        # Get the parameters.
2561        my ($keywordString) = @_;
2562        # Make a safety copy of the string. (This helps during debugging.)
2563        my $workString = $keywordString;
2564        # Convert operators we don't care about to spaces.
2565        $workString =~ tr/+"()<>/ /;
2566        # Split the rest of the string along space boundaries. Note that we
2567        # eliminate any words that are zero length or begin with a minus sign.
2568        my @wordList = grep { $_ && substr($_, 0, 1) ne "-" } split /\s+/, $workString;
2569        # Use a hash to remove duplicates.
2570        my %words = map { $_ => 1 } @wordList;
2571        # Return the result.
2572        return sort keys %words;
2573    }
2574    
2575    =head3 ValidateFieldName
2576    
2577    C<< my $okFlag = ERDB::ValidateFieldName($fieldName); >>
2578    
2579    Return TRUE if the specified field name is valid, else FALSE. Valid field names must
2580    be hyphenated words subject to certain restrictions.
2581    
2582    =over 4
2583    
2584    =item fieldName
2585    
2586    Field name to be validated.
2587    
2588    =item RETURN
2589    
2590    Returns TRUE if the field name is valid, else FALSE.
2591    
2592    =back
2593    
2594    =cut
2595    
2596    sub ValidateFieldName {
2597        # Get the parameters.
2598        my ($fieldName) = @_;
2599        # Declare the return variable. The field name is valid until we hear
2600        # differently.
2601        my $retVal = 1;
2602        # Look for bad stuff in the name.
2603        if ($fieldName =~ /--/) {
2604            # Here we have a doubled minus sign.
2605            Trace("Field name $fieldName has a doubled hyphen.") if T(1);
2606            $retVal = 0;
2607        } elsif ($fieldName !~ /^[A-Za-z]/) {
2608            # Here the field name is missing the initial letter.
2609            Trace("Field name $fieldName does not begin with a letter.") if T(1);
2610            $retVal = 0;
2611        } else {
2612            # Strip out the minus signs. Everything remaining must be a letter
2613            # or digit.
2614            my $strippedName = $fieldName;
2615            $strippedName =~ s/-//g;
2616            if ($strippedName !~ /^[A-Za-z0-9]+$/) {
2617                Trace("Field name $fieldName contains illegal characters.") if T(1);
2618                $retVal = 0;
2619            }
2620        }
2621        # Return the result.
2622        return $retVal;
2623    }
2624    
2625    =head3 ReadMetaXML
2626    
2627    C<< my $rawMetaData = ERDB::ReadDBD($fileName); >>
2628    
2629    This method reads a raw database definition XML file and returns it.
2630    Normally, the metadata used by the ERDB system has been processed and
2631    modified to make it easier to load and retrieve the data; however,
2632    this method can be used to get the data in its raw form.
2633    
2634    =over 4
2635    
2636    =item fileName
2637    
2638    Name of the XML file to read.
2639    
2640    =item RETURN
2641    
2642    Returns a hash reference containing the raw XML data from the specified file.
2643    
2644    =back
2645    
2646    =cut
2647    
2648    sub ReadMetaXML {
2649        # Get the parameters.
2650        my ($fileName) = @_;
2651        # Read the XML.
2652        my $retVal = XML::Simple::XMLin($fileName, %XmlOptions, %XmlInOpts);
2653        Trace("XML metadata loaded from file $fileName.") if T(1);
2654        # Return the result.
2655        return $retVal;
2656    }
2657    
2658    =head3 GetEntityFieldHash
2659    
2660    C<< my $fieldHashRef = ERDB::GetEntityFieldHash($structure, $entityName); >>
2661    
2662    Get the field hash of the named entity in the specified raw XML structure.
2663    The field hash may not exist, in which case we need to create it.
2664    
2665    =over 4
2666    
2667    =item structure
2668    
2669    Raw XML structure defininng the database. This is not the run-time XML used by
2670    an ERDB object, since that has all sorts of optimizations built-in.
2671    
2672    =item entityName
2673    
2674    Name of the entity whose field structure is desired.
2675    
2676    =item RETURN
2677    
2678    Returns the field hash used to define the entity's fields.
2679    
2680    =back
2681    
2682    =cut
2683    
2684    sub GetEntityFieldHash {
2685        # Get the parameters.
2686        my ($structure, $entityName) = @_;
2687        # Get the entity structure.
2688        my $entityData = $structure->{Entities}->{$entityName};
2689        # Look for a field structure.
2690        my $retVal = $entityData->{Fields};
2691        # If it doesn't exist, create it.
2692        if (! defined($retVal)) {
2693            $entityData->{Fields} = {};
2694            $retVal = $entityData->{Fields};
2695        }
2696        # Return the result.
2697        return $retVal;
2698    }
2699    
2700    =head3 WriteMetaXML
2701    
2702    C<< ERDB::WriteMetaXML($structure, $fileName); >>
2703    
2704    Write the metadata XML to a file. This method is the reverse of L</ReadMetaXML>, and is
2705    used to update the database definition. It must be used with care, however, since it
2706    will only work on a raw structure, not on the processed structure created by an ERDB
2707    constructor.
2708    
2709    =over 4
2710    
2711    =item structure
2712    
2713    XML structure to be written to the file.
2714    
2715    =item fileName
2716    
2717    Name of the output file to which the updated XML should be stored.
2718    
2719    =back
2720    
2721    =cut
2722    
2723    sub WriteMetaXML {
2724        # Get the parameters.
2725        my ($structure, $fileName) = @_;
2726        # Compute the output.
2727        my $fileString = XML::Simple::XMLout($structure, %XmlOptions, %XmlOutOpts);
2728        # Write it to the file.
2729        my $xmlOut = Open(undef, ">$fileName");
2730        print $xmlOut $fileString;
2731    }
2732    
2733    
2734    =head3 HTMLNote
2735    
2736    Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes
2737    supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.
2738    Except for C<[p]>, all the codes are closed by slash-codes. So, for
2739    example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.
2740    
2741    C<< my $realHtml = ERDB::HTMLNote($dataString); >>
2742    
2743    =over 4
2744    
2745    =item dataString
2746    
2747    String to convert to HTML.
2748    
2749    =item RETURN
2750    
2751    An HTML string derived from the input string.
2752    
2753    =back
2754    
2755    =cut
2756    
2757    sub HTMLNote {
2758        # Get the parameter.
2759        my ($dataString) = @_;
2760        # HTML-escape the text.
2761        my $retVal = CGI::escapeHTML($dataString);
2762        # Substitute the bulletin board codes.
2763        $retVal =~ s!\[(/?[bi])\]!<$1>!g;
2764        $retVal =~ s!\[p\]!</p><p>!g;
2765        # Return the result.
2766        return $retVal;
2767    }
2768    
2769    
2770  =head2 Data Mining Methods  =head2 Data Mining Methods
2771    
2772  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
# Line 2649  Line 2959 
2959      return $retVal;      return $retVal;
2960  }  }
2961    
2962    =head3 GetSourceObject
2963    
2964    C<< my $source = $erdb->GetSourceObject($entityName); >>
2965    
2966    Return the object to be used in loading special attributes of the specified entity. The
2967    algorithm for loading special attributes is stored in the C<DataGen> elements of the
2968    XML
2969    
2970  =head2 Internal Utility Methods  =head2 Internal Utility Methods
2971    
2972  =head3 _RelationMap  =head3 _RelationMap
# Line 2991  Line 3309 
3309      return Stats->new();      return Stats->new();
3310  }  }
3311    
 =head3 _GenerateFields  
   
 Generate field values from a field structure and store in a specified table. The field names  
 are first sorted by pass count, certain pre-defined fields are removed from the list, and  
 then we rip through them evaluation the data generation string. Fields in the primary relation  
 are stored as scalars; fields in secondary relations are stored as value lists.  
   
 This is a static method.  
   
 =over 4  
   
 =item this  
   
 Hash table into which the field values should be placed.  
   
 =item fields  
   
 Field structure from which the field descriptors should be taken.  
   
 =item type  
   
 Type name of the object whose fields are being generated.  
   
 =item values (optional)  
   
 Reference to a value structure from which additional values can be taken.  
   
 =item from (optiona)  
   
 Reference to the source entity instance if relationship data is being generated.  
   
 =item to (optional)  
   
 Reference to the target entity instance if relationship data is being generated.  
   
 =back  
   
 =cut  
   
 sub _GenerateFields {  
     # Get the parameters.  
     my ($this, $fields, $type, $values, $from, $to) = @_;  
     # Sort the field names by pass number.  
     my @fieldNames = sort { $fields->{$a}->{DataGen}->{pass} <=> $fields->{$b}->{DataGen}->{pass} } keys %{$fields};  
     # Loop through the field names, generating data.  
     for my $name (@fieldNames) {  
         # Only proceed if this field needs to be generated.  
         if (!exists $this->{$name}) {  
             # Get this field's data generation descriptor.  
             my $fieldDescriptor = $fields->{$name};  
             my $data = $fieldDescriptor->{DataGen};  
             # Get the code to generate the field value.  
             my $codeString = $data->{content};  
             # Determine whether or not this field is in the primary relation.  
             if ($fieldDescriptor->{relation} eq $type) {  
                 # Here we have a primary relation field. Store the field value as  
                 # a scalar.  
                 $this->{$name} = eval($codeString);  
             } else {  
                 # Here we have a secondary relation field. Create a null list  
                 # and push the desired number of field values onto it.  
                 my @fieldValues = ();  
                 my $count = IntGen(0,$data->{testCount});  
                 for (my $i = 0; $i < $count; $i++) {  
                     my $newValue = eval($codeString);  
                     push @fieldValues, $newValue;  
                 }  
                 # Store the value list in the main hash.  
                 $this->{$name} = \@fieldValues;  
             }  
         }  
     }  
 }  
   
3312  =head3 _DumpRelation  =head3 _DumpRelation
3313    
3314  Dump the specified relation's to the specified output file in tab-delimited format.  Dump the specified relation to the specified output file in tab-delimited format.
3315    
3316  This is an instance method.  This is an instance method.
3317    
# Line 3212  Line 3456 
3456          for my $object (values %{$metadata->{$section}}) {          for my $object (values %{$metadata->{$section}}) {
3457              # Loop through the object's fields.              # Loop through the object's fields.
3458              for my $fieldName (keys %{$object->{Fields}}) {              for my $fieldName (keys %{$object->{Fields}}) {
3459                  # Now we make some initial validations.                  # If this field name is invalid, set the return value to zero
3460                  if ($fieldName =~ /--/) {                  # so we know we encountered an error.
3461                      # Here we have a doubled minus sign.                  if (! ValidateFieldName($fieldName)) {
                     print STDERR "Field name $fieldName has a doubled hyphen.\n";  
                     $retVal = 0;  
                 } elsif ($fieldName !~ /^[A-Za-z]/) {  
                     # Here the field name is missing the initial letter.  
                     print STDERR "Field name $fieldName does not begin with a letter.\n";  
3462                      $retVal = 0;                      $retVal = 0;
                 } else {  
                     # Strip out the minus signs. Everything remaining must be a letter  
                     # or digit.  
                     my $strippedName = $fieldName;  
                     $strippedName =~ s/-//g;  
                     if ($strippedName !~ /^[A-Za-z0-9]+$/) {  
                         print STDERR "Field name $fieldName contains illegal characters.\n";  
                         $retVal = 0;  
                     }  
3463                  }                  }
3464              }              }
3465          }          }
# Line 3300  Line 3530 
3530      return $retVal;      return $retVal;
3531  }  }
3532    
3533    
3534  =head3 _LoadMetaData  =head3 _LoadMetaData
3535    
3536  This method loads the data describing this database from an XML file into a metadata structure.  This method loads the data describing this database from an XML file into a metadata structure.
# Line 3328  Line 3559 
3559      Trace("Reading Sprout DBD from $filename.") if T(2);      Trace("Reading Sprout DBD from $filename.") if T(2);
3560      # Slurp the XML file into a variable. Extensive use of options is used to insure we      # Slurp the XML file into a variable. Extensive use of options is used to insure we
3561      # get the exact structure we want.      # get the exact structure we want.
3562      my $metadata = XML::Simple::XMLin($filename,      my $metadata = ReadMetaXML($filename);
                                       GroupTags => { Relationships => 'Relationship',  
                                                      Entities => 'Entity',  
                                                      Fields => 'Field',  
                                                      Indexes => 'Index',  
                                                      IndexFields => 'IndexField'},  
                                       KeyAttr => { Relationship => 'name',  
                                                    Entity => 'name',  
                                                    Field => 'name'},  
                                       ForceArray => ['Field', 'Index', 'IndexField'],  
                                       ForceContent => 1,  
                                       NormalizeSpace => 2  
                                       );  
     Trace("XML metadata loaded from file $filename.") if T(1);  
3563      # Before we go any farther, we need to validate the field and object names. If an error is found,      # Before we go any farther, we need to validate the field and object names. If an error is found,
3564      # the method below will fail.      # the method below will fail.
3565      _ValidateFieldNames($metadata);      _ValidateFieldNames($metadata);
# Line 3768  Line 3986 
3986              my $type = $fieldData->{type};              my $type = $fieldData->{type};
3987              # Plug in a relation name if it is needed.              # Plug in a relation name if it is needed.
3988              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });              Tracer::MergeOptions($fieldData, { relation => $defaultRelationName });
             # Plug in a data generator if we need one.  
             if (!exists $fieldData->{DataGen}) {  
                 # The data generator will use the default for the field's type.  
                 $fieldData->{DataGen} = { content => $TypeTable{$type}->{dataGen} };  
             }  
3989              # Check for searchability.              # Check for searchability.
3990              if ($fieldData->{searchable}) {              if ($fieldData->{searchable}) {
3991                  # Only allow this for a primary relation.                  # Only allow this for a primary relation.
# Line 3782  Line 3995 
3995                      push @textFields, $fieldName;                      push @textFields, $fieldName;
3996                  }                  }
3997              }              }
             # Plug in the defaults for the optional data generation parameters.  
             Tracer::MergeOptions($fieldData->{DataGen}, { testCount => 1, pass => 0 });  
3998              # Add the PrettySortValue.              # Add the PrettySortValue.
3999              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);              $fieldData->{PrettySort} = (($type eq "text") ? $textPrettySortValue : $prettySortValue);
4000          }          }
# Line 4142  Line 4353 
4353          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";          $htmlString .= "<li><b>Index $fullName</b>\n<ul>\n";
4354          # Add any note text.          # Add any note text.
4355          if (my $note = $indexData->{Notes}) {          if (my $note = $indexData->{Notes}) {
4356              $htmlString .= "<li>" . _HTMLNote($note->{content}) . "</li>\n";              $htmlString .= "<li>" . HTMLNote($note->{content}) . "</li>\n";
4357          }          }
4358          # Add the fiield list.          # Add the fiield list.
4359          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";          $htmlString .= "<li><i>" . join(', ', @{$indexData->{IndexFields}}) . "</i></li>\n";
# Line 4257  Line 4468 
4468      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";      my $htmlString = "<tr><th align=\"left\">$fieldData->{name}</th><td>$fieldData->{type}</td>";
4469      # If we have content, add it as a third column.      # If we have content, add it as a third column.
4470      if (exists $fieldData->{Notes}) {      if (exists $fieldData->{Notes}) {
4471          $htmlString .= "<td>" . _HTMLNote($fieldData->{Notes}->{content}) . "</td>";          $htmlString .= "<td>" . HTMLNote($fieldData->{Notes}->{content}) . "</td>";
4472      }      }
4473      # Close off the row.      # Close off the row.
4474      $htmlString .= "</tr>\n";      $htmlString .= "</tr>\n";
# Line 4265  Line 4476 
4476      return $htmlString;      return $htmlString;
4477  }  }
4478    
 =head3 _HTMLNote  
   
 Convert a note or comment to HTML by replacing some bulletin-board codes with HTML. The codes  
 supported are C<[b]> for B<bold>, C<[i]> for I<italics>, and C<[p]> for a new paragraph.  
 Except for C<[p]>, all the codes are closed by slash-codes. So, for  
 example, C<[b]Feature[/b]> displays the string C<Feature> in boldface.  
   
 This is a static method.  
   
 =over 4  
   
 =item dataString  
   
 String to convert to HTML.  
   
 =item RETURN  
   
 An HTML string derived from the input string.  
   
 =back  
   
 =cut  
   
 sub _HTMLNote {  
     # Get the parameter.  
     my ($dataString) = @_;  
     # Substitute the codes.  
     $dataString =~ s!\[(/?[bi])\]!<$1>!g;  
     $dataString =~ s!\[p\]!</p><p>!g;  
     # Return the result.  
     return $dataString;  
 }  
   
 =head2 Data Generation Utilities  
   
 =head3 IntGen  
   
 C<< my $integer = IntGen($min, $max); >>  
   
 Returns a random number between the specified minimum and maximum (inclusive).  
   
 =over 4  
   
 =item min  
   
 Minimum permissible return value.  
   
 =item max  
   
 Maximum permissible return value.  
   
 =item RETURN  
   
 Returns a value no lower than the minimum and no greater than the maximum.  
   
 =back  
   
 =cut  
   
 sub IntGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Determine the range of possible values. Note we put some space well above the  
     # maximum value to give it a fighting chance of apppearing in the list.  
     my $span = $max + 0.99 - $min;  
     # Create an integer in the range.  
     my $retVal = $min + int(rand($span));  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandChar  
   
 C<< my $char = RandChar($sourceString); >>  
   
 Select a random character from a string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random character should be selected.  
   
 =item RETURN  
   
 Returns a single character from the incoming string.  
   
 =back  
   
 =cut  
   
 sub RandChar {  
     # Get the parameter.  
     my ($sourceString) = @_;  
     # Select a random character.  
     my $retVal = IntGen(0, (length $sourceString) - 1);  
     # Return it.  
     return substr($sourceString, $retVal, 1);  
 }  
   
 =head3 RandChars  
   
 C<< my $string = RandChars($sourceString, $length); >>  
   
 Create a string from characters taken from a source string.  
   
 =over 4  
   
 =item sourceString  
   
 String from which the random characters should be selected.  
   
 =item length  
   
 Number of characters to put in the output string.  
   
 =item RETURN  
   
 Returns a string of the specified length consisting of characters taken from the  
 source string.  
   
 =back  
   
 =cut  
   
 sub RandChars {  
     # Get the parameters.  
     my ($sourceString, $length) = @_;  
     # Call RandChar repeatedly to generate the string.  
     my $retVal = "";  
     for (my $i = 0; $i < $length; $i++) {  
         $retVal .= RandChar($sourceString);  
     }  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 RandParam  
   
 C<< my $value = RandParam($parm1, $parm2, ... $parmN); >>  
   
 Return a randomly-selected value from the parameter list.  
   
 =over 4  
   
 =item parm1, parm2, ... parmN  
   
 List of values of which one will be selected.  
   
 =item RETURN  
   
 Returns a randomly-chosen value from the specified list.  
   
 =back  
   
 =cut  
   
 sub RandParam {  
     # Get the parameter.  
     my @parms = @_;  
     # Choose a random parameter from the list.  
     my $chosenIndex = IntGen(0, $#parms);  
     return $parms[$chosenIndex];  
 }  
   
 =head3 StringGen  
   
 C<< my $string = StringGen($pattern1, $pattern2, ... $patternN); >>  
   
 Returns a random string derived from a randomly-chosen format pattern. The pattern  
 can either be a number (indicating the number of characters desired, or the letter  
 C<P> followed by a picture. The picture should contain C<A> when a letter is desired,  
 C<9> when a digit is desired, C<V> when a vowel is desired, C<K> when a consonant is  
 desired, and C<X> when a letter or a digit is desired. Any other character will be  
 translated as a literal.  
   
 =over 4  
   
 =item pattern1, pattern2, ... patternN  
   
 List of patterns to be used to generate string values.  
   
 =item RETURN  
   
 A single string generated from a pattern.  
   
 =back  
   
 =cut  
   
 sub StringGen {  
     # Get the parameters.  
     my @patterns = @_;  
     # Choose the appropriate pattern.  
     my $chosenPattern = RandParam(@patterns);  
     # Declare the return variable.  
     my $retVal = "";  
     # Determine whether this is a count or a picture pattern.  
     if ($chosenPattern =~ m/^\d+/) {  
         # Here we have a count. Get the string of source characters.  
         my $letterString = $PictureTable{'X'};  
         my $stringLen = length $letterString;  
         # Save the number of characters we have to generate.  
         my $charsLeft = $chosenPattern;  
         # Loop until the return variable is full.  
         while ($charsLeft > 0) {  
             # Generate a random position in the soruce string.  
             my $stringIndex = IntGen(0, $stringLen - 1);  
             # Compute the number of characters to pull out of the source string.  
             my $chunkSize = $stringLen - $stringIndex;  
             if ($chunkSize > $charsLeft) { $chunkSize = $charsLeft; }  
             # Stuff this chunk into the return value.  
             $retVal .= substr($letterString, $stringIndex, $chunkSize);  
             # Record the data moved.  
             $charsLeft -= $chunkSize;  
         }  
     } elsif ($chosenPattern =~ m/^P/) {  
         # Here we have a picture string. We will move through the picture one  
         # character at a time generating data.  
         for (my $i = 1; $i < length $chosenPattern; $i++) {  
             # Get this picture character.  
             my $chr = substr($chosenPattern, $i, 1);  
             # Check to see if the picture char is one we recognize.  
             if (exists $PictureTable{$chr}) {  
                 # Choose a random character from the available values for this  
                 # picture character.  
                 $retVal .= RandChar($PictureTable{$chr});  
             } else {  
                 # Copy in the picture character as a literal.  
                 $retVal .= $chr;  
             }  
         }  
     } else {  
         # Here we have neither a picture string or a letter count, so we treat  
         # the string as a literal.  
         $retVal = $chosenPattern;  
     }  
     # Return the string formed.  
     return $retVal;  
 }  
   
 =head3 DateGen  
   
 C<< my $date = DateGen($startDayOffset, $endDayOffset, $minutes); >>  
   
 Return a numeric timestamp within the specified range of days with the specified minute  
 value. The range of days is specified relevant to the current day. Thus, the call  
   
 C<< my $date = DateGen(-1, 5, 720); >>  
   
 will return a timestamp at noon (72 minutes past midnight) sometime during the week that  
 began on the preceding day. If you want a random minute of the day, simply combine with  
 a call to L</IntGen>, as follows.  
   
 C<< my $date = DateGen(-1, 5, IntGen(0, 1439)); >>  
   
 =over 4  
   
 =item startDayOffset  
   
 The earliest day that can be returned, relative to the current day.  
   
 =item endDayOffset  
   
 The latest day that can be returned, related to the current day.  
   
 =item minutes  
   
 Number of minutes into the selected day that should be used.  
   
 =back  
   
 =cut  
   
 sub DateGen {  
     # Get the parameters.  
     my ($startDayOffset, $endDayOffset, $minutes) = @_;  
     # Get midnight of the current day.  
     my $now = time();  
     my ($sec, $min, $hour) = localtime($now);  
     my $today = $now - (($hour * 60 + $min) * 60 + $sec);  
     # Compute the day we want.  
     my $newDay = IntGen($startDayOffset, $endDayOffset) * 86400 + $today;  
     # Add the minutes.  
     my $retVal = $newDay + $minutes * 60;  
     # Return the result.  
     return $retVal;  
 }  
   
 =head3 FloatGen  
   
 C<< my $number = FloatGen($min, $max); >>  
   
 Return a random floating-point number greater than or equal to the specified minimum and  
 less than the specified maximum.  
   
 =over 4  
   
 =item min  
   
 Minimum permissible value for the number returned.  
   
 =item max  
   
 Maximum permissible value for the number returned.  
   
 =item RETURN  
   
 Returns a floating-point number anywhere in the specified range.  
   
 =back  
   
 =cut  
   
 sub FloatGen {  
     # Get the parameters.  
     my ($min, $max) = @_;  
     # Generate the result.  
     my $retVal = rand($max - $min) + $min;  
     return $retVal;  
 }  
   
 =head3 ListGen  
   
 C<< my @list = ListGen($pattern, $count); >>  
   
 Return a list containing a fixed number of randomly-generated strings.  
   
 =over 4  
   
 =item pattern  
   
 A pattern (in the form expected by L</StringGen>) that should be used to generate the  
 strings in the list.  
   
 =item count  
   
 The number of list entries to generate.  
   
 =item RETURN  
   
 Returns a list consisting of the specified number of strings.  
   
 =back  
   
 =cut  
   
 sub ListGen {  
     # Get the parameters.  
     my ($pattern, $count) = @_;  
     # Generate the list.  
     my @retVal = ();  
     for (my $i = 0; $i < $count; $i++) {  
         push @retVal, StringGen($pattern);  
     }  
     # Return it.  
     return @retVal;  
 }  
   
4479  1;  1;

Legend:
Removed from v.1.72  
changed lines
  Added in v.1.73

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3