Find Entries with Duplicated Field Value

This script find duplicates in a chosen field and save results as a new list. It searches the datatree containing the script. This is the version with field chooser, so you specify on which field should be run the search after the script is run. There is also a minimalistic version where the field is specified directly in the script. You can find it in the dedicated forum topic.


import java.awt.Dimension
import java.awt.BorderLayout
import javax.swing.*
import javax.swing.border.*
import org.openide.*
import com.im.ijc.core.api.lists.TemporaryListsAndQueries
import com.chemaxon.df.ui.util.DFObjectListCellRenderer

def ety = dataTree.rootVertex.entity
def edp = ety.schema.dataProvider.getEntityDataProvider(ety)
def field = selectFromList(ety.fields.items)
if (field == null) {
    return
}

sort = SortDirective.create(field, true)
ids = edp.queryForIds(DFTermExpression.ALL_DATA, sort, env)

List duplicates = []
List buffer = []
lastValue = null
ids.each { rowId ->
   value = edp.getData([ rowId ], env).get(rowId).get(field.id)
   if (lastValue != value) {
       if (buffer.size() > 1) {
           duplicates.addAll(buffer)
       }
       buffer.clear()
       lastValue = value
   }
   buffer.add(rowId)
}
println "Found " + duplicates.size() + " duplicates"
if (!duplicates.empty) {
    TemporaryListsAndQueries.getListsFor(ety).addList(duplicates, "Duplicates in " + field.name + " field")
}

Object selectFromList(List values) {
    JList list = new JList(values.toArray())
    list.cellRenderer = new DFObjectListCellRenderer()
    list.selectionModel.selectionMode = ListSelectionModel.SINGLE_SELECTION
    list.visibleRowCount = 15
    panel = new JPanel()
    panel.layout = new BorderLayout()
    panel.add(new JScrollPane(list), BorderLayout.CENTER)
    panel.border = new EmptyBorder(5,5,5,5)
    panel.preferredSize = new Dimension(250, 300)
    DialogDescriptor dd = new DialogDescriptor(panel, "Select field")
    if (DialogDisplayer.getDefault().notify(dd) != DialogDescriptor.OK_OPTION) {
        println "  Cancel pressed => exit"
        return null
    }
    selected = list.selectedValue
    println "  Selected field: $selected"
    if (selected == null) {
        println "  No field selected => exit"
        return null
    }
    return selected
}

Versions: This script has been tested on IJC versions 5.9, 5.10 and 6.0



Copyright © 1999-2012 ChemAxon Ltd.    All rights reserved.