API/Samples/Groovy/Writer/MostPopularWords

About the MostPopularWords Example

This example shows how to get the text of whole document or its selected parts and how to display some statistics (exactly the most popular words) for this text in info message box in a Groovy macro.

The Code

/*
    Some OpenOffice.org API classes. For more information on
    these classes and the OpenOffice.org API, see the OpenOffice.org
    Developers Guide at:

    http://api.openoffice.org/
*/

import com.sun.star.uno.UnoRuntime
import com.sun.star.uno.XComponentContext

import com.sun.star.container.XIndexAccess
import com.sun.star.container.XNameContainer

import com.sun.star.beans.XPropertySet

import com.sun.star.frame.XDesktop
import com.sun.star.frame.XModel

import com.sun.star.awt.XWindow
import com.sun.star.awt.XWindowPeer
import com.sun.star.awt.XMessageBoxFactory
import com.sun.star.awt.XMessageBox
import com.sun.star.awt.Rectangle

import com.sun.star.lang.XComponent
import com.sun.star.lang.XMultiComponentFactory
import com.sun.star.lang.XMultiServiceFactory

import com.sun.star.view.XSelectionSupplier

import com.sun.star.text.XTextDocument
import com.sun.star.text.XTextRange
import com.sun.star.text.XText

// The number of words to display as a result
final int NW = 5
// These words should be ignored when searching for most popular words
final List<String> ignoreList = ['a', 'an', 'the', 'in', 'for', 'to', 'at', 'of', 'by', 
'and', 'or', 'nor', 'whether', 'as', 'with', 'on', 'through']

class UnoCategory {
     public static Object uno(Object unoObj, Class clazz) { UnoRuntime.queryInterface(clazz, unoObj) }
     public static Object getAt(XPropertySet pset, String pname) { pset.getPropertyValue(pname) }
     public static void putAt(XPropertySet pset, String pname, Object newValue) { pset.setPropertyValue(pname, newValue) }
     public static Object getAt(XIndexAccess ndx, int x) { ndx.getByIndex(x) }
}

// The algorithmic part of this macro
List<String> getMostPopularWords(String text, List<String> ignoreList, int count) {
	words = (text =~ /\w+/)
	freqMap = [:]
	words.each {
		String lcWord = it.toLowerCase()
		if (!ignoreList.contains(lcWord)) {
			if (null == freqMap[lcWord]) {
				freqMap[lcWord] = 1
			} else {
				freqMap[lcWord]++
			}
		}
	}
	wordList = freqMap.keySet().toList()
	wordList.sort {freqMap[it]}
	return (count >= wordList.size()) ? wordList : wordList[-1..-count]
}

// This function is used to get the text of whole document or its selected parts
String getText() {
	String text = ""

	use (UnoCategory) {
		def oDoc = XSCRIPTCONTEXT.document
		def oModel = oDoc.uno(XModel)
		def oSelectionSupplier = oModel.currentController.uno(XSelectionSupplier)
		def oIndexAccess =  oSelectionSupplier.selection.uno(XIndexAccess)
		def  count = oIndexAccess.count
		
		def xText = oDoc.uno(XTextDocument).text
		if (count > 1) {
			// More than one selection
			// Work backwards so that multiple selections stay valid.
			for (i in count - 1..0) {
				// get the XTextRange of the selection
				oTextRange =  oIndexAccess[i].uno(XTextRange)
				text += ' ' + oTextRange.string
			}
		} else {
			oTextRange =  oIndexAccess[0].uno(XTextRange)
			if (0 == oTextRange.string.size()) {
				text = xText.string
			} else {
				text = oTextRange.string
			}
		}
	}

	return text
}