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

Diff of /Sprout/ERDB.pm

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

revision 1.24, Wed Oct 12 02:56:04 2005 UTC revision 1.33, Sat Jan 28 09:36:47 2006 UTC
# Line 309  Line 309 
309                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },
310                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
311                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },
312                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   2, dataGen => "IntGen(0, 1)" },                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },
313                   'key-string' =>                   'key-string' =>
314                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },
315                   'name-string' =>                   'name-string' =>
# Line 508  Line 508 
508          # Separate out the source, the target, and the join clause.          # Separate out the source, the target, and the join clause.
509          $joinKey =~ m!^([^/]+)/(.+)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
510          my ($sourceRelation, $targetRelation) = ($1, $2);          my ($sourceRelation, $targetRelation) = ($1, $2);
511          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
512          my $source = $self->ComputeObjectSentence($sourceRelation);          my $source = $self->ComputeObjectSentence($sourceRelation);
513          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
514          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
# Line 632  Line 632 
632      }      }
633  }  }
634    
635    =head3 VerifyFields
636    
637    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
638    
639    Run through the list of proposed field values, insuring that all the character fields are
640    below the maximum length. If any fields are too long, they will be truncated in place.
641    
642    =over 4
643    
644    =item relName
645    
646    Name of the relation for which the specified fields are destined.
647    
648    =item fieldList
649    
650    Reference to a list, in order, of the fields to be put into the relation.
651    
652    =item RETURN
653    
654    Returns the number of fields truncated.
655    
656    =back
657    
658    =cut
659    
660    sub VerifyFields {
661        # Get the parameters.
662        my ($self, $relName, $fieldList) = @_;
663        # Initialize the return value.
664        my $retVal = 0;
665        # Get the relation definition.
666        my $relData = $self->_FindRelation($relName);
667        # Get the list of field descriptors.
668        my $fieldTypes = $relData->{Fields};
669        my $fieldCount = scalar @{$fieldTypes};
670        # Loop through the two lists.
671        for (my $i = 0; $i < $fieldCount; $i++) {
672            # Get the type of the current field.
673            my $fieldType = $fieldTypes->[$i]->{type};
674            # If it's a character field, verify the length.
675            if ($fieldType =~ /string/) {
676                my $maxLen = $TypeTable{$fieldType}->{maxLen};
677                my $oldString = $fieldList->[$i];
678                if (length($oldString) > $maxLen) {
679                    # Here it's too big, so we truncate it.
680                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
681                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
682                    $retVal++;
683                }
684            }
685        }
686        # Return the truncation count.
687        return $retVal;
688    }
689    
690  =head3 CreateIndex  =head3 CreateIndex
691    
692  C<< $erdb->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
# Line 851  Line 906 
906    
907  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
908    
909    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
910    be processed. The idea is to make it less likely to find the verb by accident.
911    
912  The rules for field references in a sort order are the same as those for field references in the  The rules for field references in a sort order are the same as those for field references in the
913  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
914  relation.  relation.
# Line 959  Line 1017 
1017                  $lastObject = $thisObject;                  $lastObject = $thisObject;
1018              }              }
1019          }          }
1020          # Now we need to handle the whole ORDER BY thing. We'll put the order by clause          # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
1021          # in the following variable.          # here is we want the filter clause to be empty if there's no WHERE filter.
1022            # We'll put the ORDER BY / LIMIT clauses in the following variable.
1023          my $orderClause = "";          my $orderClause = "";
1024          # Locate the ORDER BY verb (if any).          # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
1025          if ($filterString =~ m/^(.*)ORDER BY/g) {          # operator so that we find the first occurrence of either verb.
1026              # Here we have an ORDER BY verb. Split it off of the filter string.          if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
1027                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
1028              my $pos = pos $filterString;              my $pos = pos $filterString;
1029              $orderClause = substr($filterString, $pos);              $orderClause = $2 . substr($filterString, $pos);
1030              $filterString = $1;              $filterString = $1;
1031          }          }
1032          # Add the filter and the join clauses (if any) to the SELECT command.          # Add the filter and the join clauses (if any) to the SELECT command.
# Line 976  Line 1036 
1036          if (@joinWhere) {          if (@joinWhere) {
1037              $command .= " WHERE " . join(' AND ', @joinWhere);              $command .= " WHERE " . join(' AND ', @joinWhere);
1038          }          }
1039          # Add the sort clause (if any) to the SELECT command.          # Add the sort or limit clause (if any) to the SELECT command.
1040          if ($orderClause) {          if ($orderClause) {
1041              $command .= " ORDER BY $orderClause";              $command .= " $orderClause";
1042          }          }
1043      }      }
1044      Trace("SQL query: $command") if T(3);      Trace("SQL query: $command") if T(SQL => 4);
1045      Trace("PARMS: '" . (join "', '", @params) . "'") if (T(4) && (@params > 0));      Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));
1046      my $sth = $dbh->prepare_command($command);      my $sth = $dbh->prepare_command($command);
1047      # Execute it with the parameters bound in.      # Execute it with the parameters bound in.
1048      $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());      $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());
# Line 991  Line 1051 
1051      return $retVal;      return $retVal;
1052  }  }
1053    
1054    =head3 Delete
1055    
1056    C<< my $stats = $erdb->Delete($entityName, $objectID); >>
1057    
1058    Delete an entity instance from the database. The instance is deleted along with all entity and
1059    relationship instances dependent on it. The idea of dependence here is recursive. An object is
1060    always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1061    relationship connected to a dependent entity or the "to" entity connected to a 1-to-many
1062    dependent relationship.
1063    
1064    =over 4
1065    
1066    =item entityName
1067    
1068    Name of the entity type for the instance being deleted.
1069    
1070    =item objectID
1071    
1072    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1073    then it is presumed to by a LIKE pattern.
1074    
1075    =item testFlag
1076    
1077    If TRUE, the delete statements will be traced without being executed.
1078    
1079    =item RETURN
1080    
1081    Returns a statistics object indicating how many records of each particular table were
1082    deleted.
1083    
1084    =back
1085    
1086    =cut
1087    #: Return Type $%;
1088    sub Delete {
1089        # Get the parameters.
1090        my ($self, $entityName, $objectID, $testFlag) = @_;
1091        # Declare the return variable.
1092        my $retVal = Stats->new();
1093        # Get the DBKernel object.
1094        my $db = $self->{_dbh};
1095        # We're going to generate all the paths branching out from the starting entity. One of
1096        # the things we have to be careful about is preventing loops. We'll use a hash to
1097        # determine if we've hit a loop.
1098        my %alreadyFound = ();
1099        # These next lists will serve as our result stack. We start by pushing object lists onto
1100        # the stack, and then popping them off to do the deletes. This means the deletes will
1101        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1102        # sure we don't delete records that might be needed to forge relationships back to the
1103        # original item. We have two lists-- one for TO-relationships, and one for
1104        # FROM-relationships and entities.
1105        my @fromPathList = ();
1106        my @toPathList = ();
1107        # This final hash is used to remember what work still needs to be done. We push paths
1108        # onto the list, then pop them off to extend the paths. We prime it with the starting
1109        # point. Note that we will work hard to insure that the last item on a path in the
1110        # TODO list is always an entity.
1111        my @todoList = ([$entityName]);
1112        while (@todoList) {
1113            # Get the current path.
1114            my $current = pop @todoList;
1115            # Copy it into a list.
1116            my @stackedPath = @{$current};
1117            # Pull off the last item on the path. It will always be an entity.
1118            my $entityName = pop @stackedPath;
1119            # Add it to the alreadyFound list.
1120            $alreadyFound{$entityName} = 1;
1121            # Get the entity data.
1122            my $entityData = $self->_GetStructure($entityName);
1123            # The first task is to loop through the entity's relation. A DELETE command will
1124            # be needed for each of them.
1125            my $relations = $entityData->{Relations};
1126            for my $relation (keys %{$relations}) {
1127                my @augmentedList = (@stackedPath, $relation);
1128                push @fromPathList, \@augmentedList;
1129            }
1130            # Now we need to look for relationships connected to this entity.
1131            my $relationshipList = $self->{_metaData}->{Relationships};
1132            for my $relationshipName (keys %{$relationshipList}) {
1133                my $relationship = $relationshipList->{$relationshipName};
1134                # Check the FROM field. We're only interested if it's us.
1135                if ($relationship->{from} eq $entityName) {
1136                    # Add the path to this relationship.
1137                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1138                    push @fromPathList, \@augmentedList;
1139                    # Check the arity. If it's MM we're done. If it's 1M
1140                    # and the target hasn't been seen yet, we want to
1141                    # stack the entity for future processing.
1142                    if ($relationship->{arity} eq '1M') {
1143                        my $toEntity = $relationship->{to};
1144                        if (! exists $alreadyFound{$toEntity}) {
1145                            # Here we have a new entity that's dependent on
1146                            # the current entity, so we need to stack it.
1147                            my @stackList = (@augmentedList, $toEntity);
1148                            push @fromPathList, \@stackList;
1149                        }
1150                    }
1151                }
1152                # Now check the TO field. In this case only the relationship needs
1153                # deletion.
1154                if ($relationship->{to} eq $entityName) {
1155                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1156                    push @toPathList, \@augmentedList;
1157                }
1158            }
1159        }
1160        # Create the first qualifier for the WHERE clause. This selects the
1161        # keys of the primary entity records to be deleted. When we're deleting
1162        # from a dependent table, we construct a join page from the first qualifier
1163        # to the table containing the dependent records to delete.
1164        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1165        # We need to make two passes. The first is through the to-list, and
1166        # the second through the from-list. The from-list is second because
1167        # the to-list may need to pass through some of the entities the
1168        # from-list would delete.
1169        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1170        # Now it's time to do the deletes. We do it in two passes.
1171        for my $keyName ('to_link', 'from_link') {
1172            # Get the list for this key.
1173            my @pathList = @{$stackList{$keyName}};
1174            # Loop through this list.
1175            while (my $path = pop @pathList) {
1176                # Get the table whose rows are to be deleted.
1177                my @pathTables = @{$path};
1178                # Start the DELETE statement.
1179                my $target = $pathTables[$#pathTables];
1180                my $stmt = "DELETE FROM $target";
1181                # If there's more than just the one table, we need a USING clause.
1182                if (@pathTables > 1) {
1183                    $stmt .= " USING " . join(", ", @pathTables[0 .. ($#pathTables - 1)]);
1184                }
1185                # Now start the WHERE. The first thing is the ID field from the starting table. That
1186                # starting table will either be the entity relation or one of the entity's
1187                # sub-relations.
1188                $stmt .= " WHERE $pathTables[0].id $qualifier";
1189                # Now we run through the remaining entities in the path, connecting them up.
1190                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1191                    # Connect the current relationship to the preceding entity.
1192                    my ($entity, $rel) = @pathTables[$i-1,$i];
1193                    # The style of connection depends on the direction of the relationship.
1194                    $stmt .= " AND $entity.id = $rel.from_link";
1195                    if ($i + 1 <= $#pathTables) {
1196                        # Here there's a next entity, so connect that to the relationship's
1197                        # to-link.
1198                        my $entity2 = $pathTables[$i+1];
1199                        $stmt .= " AND $rel.$keyName = $entity2.id";
1200                    }
1201                }
1202                # Now we have our desired DELETE statement.
1203                if ($testFlag) {
1204                    # Here the user wants to trace without executing.
1205                    Trace($stmt) if T(0);
1206                } else {
1207                    # Here we can delete. Note that the SQL method dies with a confessing
1208                    # if an error occurs, so we just go ahead and do it.
1209                    Trace("Executing delete: $stmt") if T(3);
1210                    my $rv = $db->SQL($stmt, 0, [$objectID]);
1211                    # Accumulate the statistics for this delete. The only rows deleted
1212                    # are from the target table, so we use its name to record the
1213                    # statistic.
1214                    $retVal->Add($target, $rv);
1215                }
1216            }
1217        }
1218        # Return the result.
1219        return $retVal;
1220    }
1221    
1222  =head3 GetList  =head3 GetList
1223    
1224  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
# Line 1293  Line 1521 
1521    
1522  =item RETURN  =item RETURN
1523    
1524  Returns a statistical object containing the number of records read and a list of  Returns a statistical object containing a list of the error messages.
 the error messages.  
1525    
1526  =back  =back
1527    
# Line 1308  Line 1535 
1535      Trace("Loading table $relationName from $fileName") if T(2);      Trace("Loading table $relationName from $fileName") if T(2);
1536      # Get the database handle.      # Get the database handle.
1537      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
     # Start a transaction.  
     $dbh->begin_tran;  
1538      # Get the input file size.      # Get the input file size.
1539      my $fileSize = -s $fileName;      my $fileSize = -s $fileName;
1540      # Get the relation data.      # Get the relation data.
# Line 1359  Line 1584 
1584              }              }
1585          }          }
1586      }      }
     # Commit the database changes.  
     $dbh->commit_tran;  
1587      # Analyze the table to improve performance.      # Analyze the table to improve performance.
1588      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
1589      # Return the statistics.      # Return the statistics.
# Line 1571  Line 1794 
1794      } else {      } else {
1795          push @parmList, $parameterList;          push @parmList, $parameterList;
1796      }      }
     # Create the query.  
     my $query = $self->Get($objectNames, $filterClause, @parmList);  
     # Set up a counter of the number of records read.  
     my $fetched = 0;  
1797      # Insure the counter has a value.      # Insure the counter has a value.
1798      if (!defined $count) {      if (!defined $count) {
1799          $count = 0;          $count = 0;
1800      }      }
1801        # Add the row limit to the filter clause.
1802        if ($count > 0) {
1803            $filterClause .= " LIMIT $count";
1804        }
1805        # Create the query.
1806        my $query = $self->Get($objectNames, $filterClause, @parmList);
1807        # Set up a counter of the number of records read.
1808        my $fetched = 0;
1809      # Loop through the records returned, extracting the fields. Note that if the      # Loop through the records returned, extracting the fields. Note that if the
1810      # counter is non-zero, we stop when the number of records read hits the count.      # counter is non-zero, we stop when the number of records read hits the count.
1811      my @retVal = ();      my @retVal = ();
# Line 1640  Line 1867 
1867  =cut  =cut
1868    
1869  sub _GetLoadStats {  sub _GetLoadStats {
1870      return Stats->new('records');      return Stats->new();
1871  }  }
1872    
1873  =head3 GenerateFields  =head3 GenerateFields

Legend:
Removed from v.1.24  
changed lines
  Added in v.1.33

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3