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

Diff of /Sprout/ERDB.pm

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

revision 1.55, Sat Jun 24 23:49:10 2006 UTC revision 1.61, Mon Jul 10 09:05:17 2006 UTC
# Line 91  Line 91 
91    
92  32-bit signed integer  32-bit signed integer
93    
94    =item counter
95    
96    32-bit unsigned integer
97    
98  =item date  =item date
99    
100  64-bit unsigned integer, representing a PERL date/time value  64-bit unsigned integer, representing a PERL date/time value
# Line 318  Line 322 
322  # "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
323  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation
324  # string is specified in the field definition. "avgLen" is the average byte length for estimating  # string is specified in the field definition. "avgLen" is the average byte length for estimating
325  # record sizes.  # record sizes. "sort" is the key modifier for the sort command.
326  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, sort => "",  dataGen => "StringGen('A')" },
327                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },
328                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },                    counter => { sqlType => 'INTEGER UNSIGNED',   maxLen => 20,           avgLen =>   4, sort => "n", dataGen => "IntGen(0, 99999999)" },
329                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, sort => "",  dataGen => "StringGen(IntGen(10,250))" },
330                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, sort => "",  dataGen => "StringGen(IntGen(80,1000))" },
331                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, sort => "n", dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
332                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, sort => "g", dataGen => "FloatGen(0.0, 100.0)" },
333                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, sort => "n", dataGen => "IntGen(0, 1)" },
334                   'hash-string' =>                   'hash-string' =>
335                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, sort => "",  dataGen => "SringGen(22)" },
336                   'id-string' =>                   'id-string' =>
337                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, dataGen => "SringGen(22)" },                               { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, sort => "",  dataGen => "SringGen(22)" },
338                   'key-string' =>                   'key-string' =>
339                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, sort => "",  dataGen => "StringGen(IntGen(10,40))" },
340                   'name-string' =>                   'name-string' =>
341                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,80))" },
342                   'medium-string' =>                   'medium-string' =>
343                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, sort => "",  dataGen => "StringGen(IntGen(10,160))" },
344                  );                  );
345    
346  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 1623  Line 1628 
1628  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1629  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1630    
1631  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1632    
1633  =over 4  =over 4
1634    
# Line 1833  Line 1838 
1838          }          }
1839      }      }
1840      # Analyze the table to improve performance.      # Analyze the table to improve performance.
1841        Trace("Analyzing and compacting $relationName.") if T(3);
1842      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
1843        # Flush the database cache.
1844        $dbh->flush_tables();
1845        Trace("$relationName load completed.") if T(3);
1846      # Return the statistics.      # Return the statistics.
1847      return $retVal;      return $retVal;
1848  }  }
# Line 3233  Line 3242 
3242    
3243  =head3 SortNeeded  =head3 SortNeeded
3244    
3245  C<< my $flag = $erdb->SortNeeded($relationName); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
3246    
3247    Return the pipe command for the sort that should be applied to the specified
3248    relation when creating the load file.
3249    
3250    For example, if the load file should be sorted ascending by the first
3251    field with duplicates removed, this method would return
3252    
3253  Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,      sort -k 1 -u -t "\t"
3254  else FALSE.  
3255    If the first field is numeric and duplicates are okay, the method would
3256    return
3257    
3258        sort -k 1n -t "\t"
3259    
3260  =over 4  =over 4
3261    
# Line 3244  Line 3263 
3263    
3264  Name of the relation to be examined.  Name of the relation to be examined.
3265    
3266  =item RETURN  =item
3267    
3268  Returns TRUE if the relation needs a sort, else FALSE.  Returns the sort command to use for sorting the relation, suitable for piping.
3269    
3270  =back  =back
3271    
# Line 3255  Line 3274 
3274  sub SortNeeded {  sub SortNeeded {
3275      # Get the parameters.      # Get the parameters.
3276      my ($self, $relationName) = @_;      my ($self, $relationName) = @_;
3277      # Declare the return variable.      # Declare a descriptor to hold the names of the key fields.
3278      my $retVal = 0;      my @keyNames = ();
3279      # Find out if the relation is a primary entity relation.      # Declare a flag for indicating uniqueness.
3280        my $unique;
3281        # Get the relation structure.
3282        my $relationData = $self->_FindRelation($relationName);
3283        # Find out if the relation is a primary entity relation,
3284        # a relationship relation, or a secondary entity relation.
3285      my $entityTable = $self->{_metaData}->{Entities};      my $entityTable = $self->{_metaData}->{Entities};
3286        my $relationshipTable = $self->{_metaData}->{Relationships};
3287      if (exists $entityTable->{$relationName}) {      if (exists $entityTable->{$relationName}) {
3288          my $keyType = $entityTable->{$relationName}->{keyType};          # Here we have a primary entity relation, so we have a unique sort on the
3289          Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);          # ID field.
3290          # If the key is not a hash string, we must do the sort.          $unique = "-u ";
3291          if ($keyType ne 'hash-string') {          push @keyNames, "id";
3292              $retVal = 1;      } elsif (exists $relationshipTable->{$relationName}) {
3293            # Here we have a relationship. We sort using the FROM index.
3294            $unique = "";
3295            my $relationshipData = $relationshipTable->{$relationName};
3296            my $index = $relationData->{Indexes}->{"idx${relationName}From"};
3297            push @keyNames, @{$index->{IndexFields}};
3298        } else {
3299            # Here we have a secondary entity relation, so we have a non-unique sort on
3300            # the ID field.
3301            $unique = "";
3302            push @keyNames, "id";
3303        }
3304        # Now we parse the key names into sort parameters. First, we prime the return
3305        # string.
3306        my $retVal = "sort -t \"\t\" $unique";
3307        # Get the relation's field list.
3308        my @fields = @{$relationData->{Fields}};
3309        # Loop through the keys.
3310        for my $keyData (@keyNames) {
3311            # Get the key and the ordering.
3312            my ($keyName, $ordering);
3313            if ($keyData =~ /^([^ ]+) DESC/) {
3314                ($keyName, $ordering) = ($1, "descending");
3315            } else {
3316                ($keyName, $ordering) = ($keyData, "ascending");
3317            }
3318            # Find the key's position and type.
3319            my $fieldSpec;
3320            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
3321                my $thisField = $fields[$i];
3322                if ($thisField->{name} eq $keyName) {
3323                    # Get the sort modifier for this field type. The modifier
3324                    # decides whether we're using a character, numeric, or
3325                    # floating-point sort.
3326                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
3327                    # If the index is descending for this field, denote we want
3328                    # to reverse the sort order on this field.
3329                    if ($ordering eq 'descending') {
3330                        $modifier .= "r";
3331                    }
3332                    # Store the position and modifier into the field spec, which
3333                    # will stop the inner loop.
3334                    $fieldSpec = "$i$modifier";
3335                }
3336          }          }
3337            # Add this field to the sort command.
3338            $retVal .= " -k $fieldSpec";
3339      }      }
3340      # Return the result.      # Return the result.
3341      return $retVal;      return $retVal;

Legend:
Removed from v.1.55  
changed lines
  Added in v.1.61

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3