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

Diff of /Sprout/ERDB.pm

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

revision 1.48, Wed Jun 21 03:12:20 2006 UTC revision 1.60, Sun Jul 9 21:16:12 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 1544  Line 1549 
1549      }      }
1550  }  }
1551    
1552    =head3 InsertValue
1553    
1554    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
1555    
1556    This method will insert a new value into the database. The value must be one
1557    associated with a secondary relation, since primary values cannot be inserted:
1558    they occur exactly once. Secondary values, on the other hand, can be missing
1559    or multiply-occurring.
1560    
1561    =over 4
1562    
1563    =item entityID
1564    
1565    ID of the object that is to receive the new value.
1566    
1567    =item fieldName
1568    
1569    Field name for the new value-- this includes the entity name, since
1570    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
1571    
1572    =item value
1573    
1574    New value to be put in the field.
1575    
1576    =back
1577    
1578    =cut
1579    
1580    sub InsertValue {
1581        # Get the parameters.
1582        my ($self, $entityID, $fieldName, $value) = @_;
1583        # Parse the entity name and the real field name.
1584        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
1585            my $entityName = $1;
1586            my $fieldTitle = $2;
1587            # Get its descriptor.
1588            if (!$self->IsEntity($entityName)) {
1589                Confess("$entityName is not a valid entity.");
1590            } else {
1591                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1592                # Find the relation containing this field.
1593                my $fieldHash = $entityData->{Fields};
1594                if (! exists $fieldHash->{$fieldTitle}) {
1595                    Confess("$fieldTitle not found in $entityName.");
1596                } else {
1597                    my $relation = $fieldHash->{$fieldTitle}->{relation};
1598                    if ($relation eq $entityName) {
1599                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
1600                    } else {
1601                        # Now we can create an INSERT statement.
1602                        my $dbh = $self->{_dbh};
1603                        my $fixedName = _FixName($fieldTitle);
1604                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
1605                        # Execute the command.
1606                        $dbh->SQL($statement, 0, $entityID, $value);
1607                    }
1608                }
1609            }
1610        } else {
1611            Confess("$fieldName is not a valid field name.");
1612        }
1613    }
1614    
1615  =head3 InsertObject  =head3 InsertObject
1616    
1617  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
# Line 1560  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 1771  Line 1839 
1839      }      }
1840      # Analyze the table to improve performance.      # Analyze the table to improve performance.
1841      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
1842        # Flush the database cache.
1843        $dbh->flush_tables();
1844      # Return the statistics.      # Return the statistics.
1845      return $retVal;      return $retVal;
1846  }  }
# Line 2001  Line 2071 
2071          push @retVal, \@rowData;          push @retVal, \@rowData;
2072          $fetched++;          $fetched++;
2073      }      }
2074        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2075      # Return the resulting list.      # Return the resulting list.
2076      return @retVal;      return @retVal;
2077  }  }
2078    
2079    =head3 Exists
2080    
2081    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2082    
2083    Return TRUE if an entity exists, else FALSE.
2084    
2085    =over 4
2086    
2087    =item entityName
2088    
2089    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2090    
2091    =item entityID
2092    
2093    ID of the entity instance whose existence is to be checked.
2094    
2095    =item RETURN
2096    
2097    Returns TRUE if the entity instance exists, else FALSE.
2098    
2099    =back
2100    
2101    =cut
2102    #: Return Type $;
2103    sub Exists {
2104        # Get the parameters.
2105        my ($self, $entityName, $entityID) = @_;
2106        # Check for the entity instance.
2107        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2108        my $testInstance = $self->GetEntity($entityName, $entityID);
2109        # Return an existence indicator.
2110        my $retVal = ($testInstance ? 1 : 0);
2111        return $retVal;
2112    }
2113    
2114  =head3 EstimateRowSize  =head3 EstimateRowSize
2115    
2116  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 2195  Line 2301 
2301    
2302  =head3 ParseColumns  =head3 ParseColumns
2303    
2304  C<< my @columns = ERDB->ParseColumns($line); >>  C<< my @columns = ERDB::ParseColumns($line); >>
2305    
2306  Convert the specified data line to a list of columns.  Convert the specified data line to a list of columns.
2307    
# Line 2216  Line 2322 
2322    
2323  sub ParseColumns {  sub ParseColumns {
2324      # Get the parameters.      # Get the parameters.
2325      my ($self, $line) = @_;      my ($line) = @_;
2326      # Chop off the line-end.      # Chop off the line-end.
2327      chomp $line;      chomp $line;
2328      # Split it into a list.      # Split it into a list.
# Line 3134  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 3145  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 3156  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.
3332                    $fieldSpec = "$i$modifier";
3333                }
3334          }          }
3335            # Add this field to the sort command.
3336            $retVal .= " -k $fieldSpec";
3337      }      }
3338      # Return the result.      # Return the result.
3339      return $retVal;      return $retVal;

Legend:
Removed from v.1.48  
changed lines
  Added in v.1.60

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3