[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 1.65, Tue Jul 11 06:10:41 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        Trace("$relationName load completed.") if T(3);
1844      # Return the statistics.      # Return the statistics.
1845      return $retVal;      return $retVal;
1846  }  }
# Line 3233  Line 3240 
3240    
3241  =head3 SortNeeded  =head3 SortNeeded
3242    
3243  C<< my $flag = $erdb->SortNeeded($relationName); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
3244    
3245    Return the pipe command for the sort that should be applied to the specified
3246    relation when creating the load file.
3247    
3248    For example, if the load file should be sorted ascending by the first
3249    field with duplicates removed, this method would return
3250    
3251  Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,      sort -k 1 -u -t "\t"
3252  else FALSE.  
3253    If the first field is numeric and duplicates are okay, the method would
3254    return
3255    
3256        sort -k 1n -t "\t"
3257    
3258  =over 4  =over 4
3259    
# Line 3244  Line 3261 
3261    
3262  Name of the relation to be examined.  Name of the relation to be examined.
3263    
3264  =item RETURN  =item
3265    
3266  Returns TRUE if the relation needs a sort, else FALSE.  Returns the sort command to use for sorting the relation, suitable for piping.
3267    
3268  =back  =back
3269    
# Line 3255  Line 3272 
3272  sub SortNeeded {  sub SortNeeded {
3273      # Get the parameters.      # Get the parameters.
3274      my ($self, $relationName) = @_;      my ($self, $relationName) = @_;
3275      # Declare the return variable.      # Declare a descriptor to hold the names of the key fields.
3276      my $retVal = 0;      my @keyNames = ();
3277      # Find out if the relation is a primary entity relation.      # Declare a flag for indicating uniqueness.
3278        my $unique;
3279        # Get the relation structure.
3280        my $relationData = $self->_FindRelation($relationName);
3281        # Find out if the relation is a primary entity relation,
3282        # a relationship relation, or a secondary entity relation.
3283      my $entityTable = $self->{_metaData}->{Entities};      my $entityTable = $self->{_metaData}->{Entities};
3284        my $relationshipTable = $self->{_metaData}->{Relationships};
3285      if (exists $entityTable->{$relationName}) {      if (exists $entityTable->{$relationName}) {
3286          my $keyType = $entityTable->{$relationName}->{keyType};          # Here we have a primary entity relation, so we have a unique sort on the
3287          Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);          # ID field.
3288          # If the key is not a hash string, we must do the sort.          $unique = "-u ";
3289          if ($keyType ne 'hash-string') {          push @keyNames, "id";
3290              $retVal = 1;      } elsif (exists $relationshipTable->{$relationName}) {
3291            # Here we have a relationship. We sort using the FROM index.
3292            $unique = "";
3293            my $relationshipData = $relationshipTable->{$relationName};
3294            my $index = $relationData->{Indexes}->{"idx${relationName}From"};
3295            push @keyNames, @{$index->{IndexFields}};
3296        } else {
3297            # Here we have a secondary entity relation, so we have a non-unique sort on
3298            # the ID field.
3299            $unique = "";
3300            push @keyNames, "id";
3301        }
3302        # Now we parse the key names into sort parameters. First, we prime the return
3303        # string.
3304        my $retVal = "sort -t \"\t\" $unique";
3305        # Get the relation's field list.
3306        my @fields = @{$relationData->{Fields}};
3307        # Loop through the keys.
3308        for my $keyData (@keyNames) {
3309            # Get the key and the ordering.
3310            my ($keyName, $ordering);
3311            if ($keyData =~ /^([^ ]+) DESC/) {
3312                ($keyName, $ordering) = ($1, "descending");
3313            } else {
3314                ($keyName, $ordering) = ($keyData, "ascending");
3315            }
3316            # Find the key's position and type.
3317            my $fieldSpec;
3318            for (my $i = 0; $i <= $#fields && ! $fieldSpec; $i++) {
3319                my $thisField = $fields[$i];
3320                if ($thisField->{name} eq $keyName) {
3321                    # Get the sort modifier for this field type. The modifier
3322                    # decides whether we're using a character, numeric, or
3323                    # floating-point sort.
3324                    my $modifier = $TypeTable{$thisField->{type}}->{sort};
3325                    # If the index is descending for this field, denote we want
3326                    # to reverse the sort order on this field.
3327                    if ($ordering eq 'descending') {
3328                        $modifier .= "r";
3329                    }
3330                    # Store the position and modifier into the field spec, which
3331                    # will stop the inner loop. Note that the field number is
3332                    # 1-based in the sort command, so we have to increment the
3333                    # index.
3334                    $fieldSpec = ($i + 1) . $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.1.65

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3