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

Diff of /Sprout/ERDB.pm

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

revision 1.47, Sun Jun 18 05:14:56 2006 UTC revision 1.68, Tue Sep 19 00:12:21 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 1431  Line 1436 
1436  sub GetCount {  sub GetCount {
1437      # Get the parameters.      # Get the parameters.
1438      my ($self, $objectNames, $filter, $params) = @_;      my ($self, $objectNames, $filter, $params) = @_;
1439        # Insure the params argument is an array reference if the caller left it off.
1440        if (! defined($params)) {
1441            $params = [];
1442        }
1443      # Declare the return variable.      # Declare the return variable.
1444      my $retVal;      my $retVal;
1445      # Find out if we're counting an entity or a relationship.      # Find out if we're counting an entity or a relationship.
# Line 1544  Line 1553 
1553      }      }
1554  }  }
1555    
1556    =head3 InsertValue
1557    
1558    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
1559    
1560    This method will insert a new value into the database. The value must be one
1561    associated with a secondary relation, since primary values cannot be inserted:
1562    they occur exactly once. Secondary values, on the other hand, can be missing
1563    or multiply-occurring.
1564    
1565    =over 4
1566    
1567    =item entityID
1568    
1569    ID of the object that is to receive the new value.
1570    
1571    =item fieldName
1572    
1573    Field name for the new value-- this includes the entity name, since
1574    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
1575    
1576    =item value
1577    
1578    New value to be put in the field.
1579    
1580    =back
1581    
1582    =cut
1583    
1584    sub InsertValue {
1585        # Get the parameters.
1586        my ($self, $entityID, $fieldName, $value) = @_;
1587        # Parse the entity name and the real field name.
1588        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
1589            my $entityName = $1;
1590            my $fieldTitle = $2;
1591            # Get its descriptor.
1592            if (!$self->IsEntity($entityName)) {
1593                Confess("$entityName is not a valid entity.");
1594            } else {
1595                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1596                # Find the relation containing this field.
1597                my $fieldHash = $entityData->{Fields};
1598                if (! exists $fieldHash->{$fieldTitle}) {
1599                    Confess("$fieldTitle not found in $entityName.");
1600                } else {
1601                    my $relation = $fieldHash->{$fieldTitle}->{relation};
1602                    if ($relation eq $entityName) {
1603                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
1604                    } else {
1605                        # Now we can create an INSERT statement.
1606                        my $dbh = $self->{_dbh};
1607                        my $fixedName = _FixName($fieldTitle);
1608                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
1609                        # Execute the command.
1610                        $dbh->SQL($statement, 0, $entityID, $value);
1611                    }
1612                }
1613            }
1614        } else {
1615            Confess("$fieldName is not a valid field name.");
1616        }
1617    }
1618    
1619  =head3 InsertObject  =head3 InsertObject
1620    
1621  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
# Line 1560  Line 1632 
1632  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
1633  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>.
1634    
1635  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'}); >>
1636    
1637  =over 4  =over 4
1638    
# Line 1770  Line 1842 
1842          }          }
1843      }      }
1844      # Analyze the table to improve performance.      # Analyze the table to improve performance.
1845        Trace("Analyzing and compacting $relationName.") if T(3);
1846      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
1847        Trace("$relationName load completed.") if T(3);
1848      # Return the statistics.      # Return the statistics.
1849      return $retVal;      return $retVal;
1850  }  }
# Line 1873  Line 1947 
1947    
1948  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>  C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
1949    
1950  Return a list of values from a specified entity instance.  Return a list of values from a specified entity instance. If the entity instance
1951    does not exist, an empty list is returned.
1952    
1953  =over 4  =over 4
1954    
# Line 2001  Line 2076 
2076          push @retVal, \@rowData;          push @retVal, \@rowData;
2077          $fetched++;          $fetched++;
2078      }      }
2079        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2080      # Return the resulting list.      # Return the resulting list.
2081      return @retVal;      return @retVal;
2082  }  }
2083    
2084    =head3 Exists
2085    
2086    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2087    
2088    Return TRUE if an entity exists, else FALSE.
2089    
2090    =over 4
2091    
2092    =item entityName
2093    
2094    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2095    
2096    =item entityID
2097    
2098    ID of the entity instance whose existence is to be checked.
2099    
2100    =item RETURN
2101    
2102    Returns TRUE if the entity instance exists, else FALSE.
2103    
2104    =back
2105    
2106    =cut
2107    #: Return Type $;
2108    sub Exists {
2109        # Get the parameters.
2110        my ($self, $entityName, $entityID) = @_;
2111        # Check for the entity instance.
2112        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2113        my $testInstance = $self->GetEntity($entityName, $entityID);
2114        # Return an existence indicator.
2115        my $retVal = ($testInstance ? 1 : 0);
2116        return $retVal;
2117    }
2118    
2119  =head3 EstimateRowSize  =head3 EstimateRowSize
2120    
2121  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 2072  Line 2183 
2183      return $objectData->{Fields};      return $objectData->{Fields};
2184  }  }
2185    
2186    =head2 Data Mining Methods
2187    
2188  =head3 GetUsefulCrossValues  =head3 GetUsefulCrossValues
2189    
2190  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>  C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
# Line 2133  Line 2246 
2246      return @retVal;      return @retVal;
2247  }  }
2248    
2249    =head3 FindColumn
2250    
2251    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2252    
2253    Return the location a desired column in a data mining header line. The data
2254    mining header line is a tab-separated list of column names. The column
2255    identifier is either the numerical index of a column or the actual column
2256    name.
2257    
2258    =over 4
2259    
2260    =item headerLine
2261    
2262    The header line from a data mining command, which consists of a tab-separated
2263    list of column names.
2264    
2265    =item columnIdentifier
2266    
2267    Either the ordinal number of the desired column (1-based), or the name of the
2268    desired column.
2269    
2270    =item RETURN
2271    
2272    Returns the array index (0-based) of the desired column.
2273    
2274    =back
2275    
2276    =cut
2277    
2278    sub FindColumn {
2279        # Get the parameters.
2280        my ($headerLine, $columnIdentifier) = @_;
2281        # Declare the return variable.
2282        my $retVal;
2283        # Split the header line into column names.
2284        my @headers = ParseColumns($headerLine);
2285        # Determine whether we have a number or a name.
2286        if ($columnIdentifier =~ /^\d+$/) {
2287            # Here we have a number. Subtract 1 and validate the result.
2288            $retVal = $columnIdentifier - 1;
2289            if ($retVal < 0 || $retVal > $#headers) {
2290                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
2291            }
2292        } else {
2293            # Here we have a name. We need to find it in the list.
2294            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
2295                if ($headers[$i] eq $columnIdentifier) {
2296                    $retVal = $i;
2297                }
2298            }
2299            if (! defined($retVal)) {
2300                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
2301            }
2302        }
2303        # Return the result.
2304        return $retVal;
2305    }
2306    
2307    =head3 ParseColumns
2308    
2309    C<< my @columns = ERDB::ParseColumns($line); >>
2310    
2311    Convert the specified data line to a list of columns.
2312    
2313    =over 4
2314    
2315    =item line
2316    
2317    A data mining input, consisting of a tab-separated list of columns terminated by a
2318    new-line.
2319    
2320    =item RETURN
2321    
2322    Returns a list consisting of the column values.
2323    
2324    =back
2325    
2326    =cut
2327    
2328    sub ParseColumns {
2329        # Get the parameters.
2330        my ($line) = @_;
2331        # Chop off the line-end.
2332        chomp $line;
2333        # Split it into a list.
2334        my @retVal = split(/\t/, $line);
2335        # Return the result.
2336        return @retVal;
2337    }
2338    
2339  =head2 Internal Utility Methods  =head2 Internal Utility Methods
2340    
2341  =head3 SetupSQL  =head3 SetupSQL
# Line 3042  Line 3245 
3245    
3246  =head3 SortNeeded  =head3 SortNeeded
3247    
3248  C<< my $flag = $erdb->SortNeeded($relationName); >>  C<< my $parms = $erdb->SortNeeded($relationName); >>
3249    
3250    Return the pipe command for the sort that should be applied to the specified
3251    relation when creating the load file.
3252    
3253    For example, if the load file should be sorted ascending by the first
3254    field, this method would return
3255    
3256  Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,      sort -k1 -t"\t"
3257  else FALSE.  
3258    If the first field is numeric, the method would return
3259    
3260        sort -k1n -t"\t"
3261    
3262    Unfortunately, due to a bug in the C<sort> command, we cannot eliminate duplicate
3263    keys using a sort.
3264    
3265  =over 4  =over 4
3266    
# Line 3053  Line 3268 
3268    
3269  Name of the relation to be examined.  Name of the relation to be examined.
3270    
3271  =item RETURN  =item
3272    
3273  Returns TRUE if the relation needs a sort, else FALSE.  Returns the sort command to use for sorting the relation, suitable for piping.
3274    
3275  =back  =back
3276    
# Line 3064  Line 3279 
3279  sub SortNeeded {  sub SortNeeded {
3280      # Get the parameters.      # Get the parameters.
3281      my ($self, $relationName) = @_;      my ($self, $relationName) = @_;
3282      # Declare the return variable.      # Declare a descriptor to hold the names of the key fields.
3283      my $retVal = 0;      my @keyNames = ();
3284      # Find out if the relation is a primary entity relation.      # Get the relation structure.
3285        my $relationData = $self->_FindRelation($relationName);
3286        # Find out if the relation is a primary entity relation,
3287        # a relationship relation, or a secondary entity relation.
3288      my $entityTable = $self->{_metaData}->{Entities};      my $entityTable = $self->{_metaData}->{Entities};
3289        my $relationshipTable = $self->{_metaData}->{Relationships};
3290      if (exists $entityTable->{$relationName}) {      if (exists $entityTable->{$relationName}) {
3291          my $keyType = $entityTable->{$relationName}->{keyType};          # Here we have a primary entity relation.
3292          Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);          push @keyNames, "id";
3293          # If the key is not a hash string, we must do the sort.      } elsif (exists $relationshipTable->{$relationName}) {
3294          if ($keyType ne 'hash-string') {          # Here we have a relationship. We sort using the FROM index.
3295              $retVal = 1;          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 sort on the ID field.
3300            push @keyNames, "id";
3301        }
3302        # Now we parse the key names into sort parameters. First, we prime the return
3303        # string.
3304        my $retVal = "sort -t\"\t\" ";
3305        # Get the relation's field list.
3306        my @fields = @{$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.1.47  
changed lines
  Added in v.1.68

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3