Skip to content

Instantly share code, notes, and snippets.

@alierdogan7

alierdogan7/ABHArabicDiacritics.java

Last active August 26, 2023 22:43
Show Gist options
  • Save alierdogan7/11f9cfb24f5551c34191485fc764d4c0 to your computer and use it in GitHub Desktop.
Save alierdogan7/11f9cfb24f5551c34191485fc764d4c0 to your computer and use it in GitHub Desktop.
Download ZIP
Arabic tex view utilities
Raw
ABHArabicDiacritics.java
package ae.ftech.quraan.Utility.arabicfont;
import android.graphics.Color;
import android.text.SpannableString;
import android.text.Spanned;
import android.text.style.ForegroundColorSpan;
/**
* Created by arshadbinhamza on 11/27/16.
*/
public class ABHArabicDiacritics {
String contentText;
String serchText;
int searchTextStartPosition=-1;
int searchTextEndPosition=-1;
SpannableString searchHighlightedSpan;
public ABHArabicDiacritics(String contentText, String searchtext) {
this.contentText =contentText;
this.serchText =searchtext;
String adVersa = contentText;
String temp="";
for(int i=0;i<adVersa.length();i++)
{
temp = adVersa.substring(0,i);
if(getDiacriticinsensitive(temp).contains(searchtext))
{
searchTextEndPosition=i;
break;
}
}
if(searchTextEndPosition>-1)
{
temp="";
for(int j=searchTextEndPosition;j>=0;j--)
{
temp = adVersa.substring(j,searchTextEndPosition);
if(temp.length()>0)
if(getDiacriticinsensitive(temp).contains(searchtext))
{
searchTextStartPosition=j;
break;
}
}
}
searchHighlightedSpan = new SpannableString(contentText);
searchHighlightedSpan.setSpan(new ForegroundColorSpan(Color.RED), searchTextStartPosition>0?searchTextStartPosition-1:searchTextStartPosition, searchTextEndPosition, Spanned.SPAN_EXCLUSIVE_EXCLUSIVE);
}
public ABHArabicDiacritics() {
}
public boolean isContain()
{
if(getSearchTextEndPosition()>-1)
return true;
else return false;
}
public String getDiacriticinsensitive(String s) {
/* String normalized = Normalizer.normalize(s, Normalizer.Form.NFD);
return normalized.replaceAll("\\p{M}", "");*/
String input =s;
//Remove honorific sign
input=input.replaceAll("\u0610", "");//ARABIC SIGN SALLALLAHOU ALAYHE WA SALLAM
input=input.replaceAll("\u0611", "");//ARABIC SIGN ALAYHE ASSALLAM
input=input.replaceAll("\u0612", "");//ARABIC SIGN RAHMATULLAH ALAYHE
input=input.replaceAll("\u0613", "");//ARABIC SIGN RADI ALLAHOU ANHU
input=input.replaceAll("\u0614", "");//ARABIC SIGN TAKHALLUS
//Remove koranic anotation
input=input.replaceAll("\u0615", "");//ARABIC SMALL HIGH TAH
input=input.replaceAll("\u0616", "");//ARABIC SMALL HIGH LIGATURE ALEF WITH LAM WITH YEH
input=input.replaceAll("\u0617", "");//ARABIC SMALL HIGH ZAIN
input=input.replaceAll("\u0618", "");//ARABIC SMALL FATHA
input=input.replaceAll("\u0619", "");//ARABIC SMALL DAMMA
input=input.replaceAll("\u061A", "");//ARABIC SMALL KASRA
input=input.replaceAll("\u06D6", "");//ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA
input=input.replaceAll("\u06D7", "");//ARABIC SMALL HIGH LIGATURE QAF WITH LAM WITH ALEF MAKSURA
input=input.replaceAll("\u06D8", "");//ARABIC SMALL HIGH MEEM INITIAL FORM
input=input.replaceAll("\u06D9", "");//ARABIC SMALL HIGH LAM ALEF
input=input.replaceAll("\u06DA", "");//ARABIC SMALL HIGH JEEM
input=input.replaceAll("\u06DB", "");//ARABIC SMALL HIGH THREE DOTS
input=input.replaceAll("\u06DC", "");//ARABIC SMALL HIGH SEEN
input=input.replaceAll("\u06DD", "");//ARABIC END OF AYAH
input=input.replaceAll("\u06DE", "");//ARABIC START OF RUB EL HIZB
input=input.replaceAll("\u06DF", "");//ARABIC SMALL HIGH ROUNDED ZERO
input=input.replaceAll("\u06E0", "");//ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO
input=input.replaceAll("\u06E1", "");//ARABIC SMALL HIGH DOTLESS HEAD OF KHAH
input=input.replaceAll("\u06E2", "");//ARABIC SMALL HIGH MEEM ISOLATED FORM
input=input.replaceAll("\u06E3", "");//ARABIC SMALL LOW SEEN
input=input.replaceAll("\u06E4", "");//ARABIC SMALL HIGH MADDA
input=input.replaceAll("\u06E5", "");//ARABIC SMALL WAW
input=input.replaceAll("\u06E6", "");//ARABIC SMALL YEH
input=input.replaceAll("\u06E7", "");//ARABIC SMALL HIGH YEH
input=input.replaceAll("\u06E8", "");//ARABIC SMALL HIGH NOON
input=input.replaceAll("\u06E9", "");//ARABIC PLACE OF SAJDAH
input=input.replaceAll("\u06EA", "");//ARABIC EMPTY CENTRE LOW STOP
input=input.replaceAll("\u06EB", "");//ARABIC EMPTY CENTRE HIGH STOP
input=input.replaceAll("\u06EC", "");//ARABIC ROUNDED HIGH STOP WITH FILLED CENTRE
input=input.replaceAll("\u06ED", "");//ARABIC SMALL LOW MEEM
//Remove tatweel
input=input.replaceAll("\u0640", "");
//Remove tashkeel
input=input.replaceAll("\u064B", "");//ARABIC FATHATAN
input=input.replaceAll("\u064C", "");//ARABIC DAMMATAN
input=input.replaceAll("\u064D", "");//ARABIC KASRATAN
input=input.replaceAll("\u064E", "");//ARABIC FATHA
input=input.replaceAll("\u064F", "");//ARABIC DAMMA
input=input.replaceAll("\u0650", "");//ARABIC KASRA
input=input.replaceAll("\u0651", "");//ARABIC SHADDA
input=input.replaceAll("\u0652", "");//ARABIC SUKUN
input=input.replaceAll("\u0653", "");//ARABIC MADDAH ABOVE
input=input.replaceAll("\u0654", "");//ARABIC HAMZA ABOVE
input=input.replaceAll("\u0655", "");//ARABIC HAMZA BELOW
input=input.replaceAll("\u0656", "");//ARABIC SUBSCRIPT ALEF
input=input.replaceAll("\u0657", "");//ARABIC INVERTED DAMMA
input=input.replaceAll("\u0658", "");//ARABIC MARK NOON GHUNNA
input=input.replaceAll("\u0659", "");//ARABIC ZWARAKAY
input=input.replaceAll("\u065A", "");//ARABIC VOWEL SIGN SMALL V ABOVE
input=input.replaceAll("\u065B", "");//ARABIC VOWEL SIGN INVERTED SMALL V ABOVE
input=input.replaceAll("\u065C", "");//ARABIC VOWEL SIGN DOT BELOW
input=input.replaceAll("\u065D", "");//ARABIC REVERSED DAMMA
input=input.replaceAll("\u065E", "");//ARABIC FATHA WITH TWO DOTS
input=input.replaceAll("\u065F", "");//ARABIC WAVY HAMZA BELOW
input=input.replaceAll("\u0670", "");//ARABIC LETTER SUPERSCRIPT ALEF
//Replace Waw Hamza Above by Waw
input=input.replaceAll("\u0624", "\u0648");
//Replace Ta Marbuta by Ha
input=input.replaceAll("\u0629", "\u0647");
//Replace Ya
// and Ya Hamza Above by Alif Maksura
input=input.replaceAll("\u064A", "\u0649");
input=input.replaceAll("\u0626", "\u0649");
// Replace Alifs with Hamza Above/Below
// and with Madda Above by Alif
input=input.replaceAll("\u0622", "\u0627");
input=input.replaceAll("\u0623", "\u0627");
input=input.replaceAll("\u0625", "\u0627");
return input;
}
public String getContentText() {
return contentText;
}
public void setContentText(String contentText) {
this.contentText = contentText;
}
public String getSerchText() {
return serchText;
}
public void setSerchText(String serchText) {
this.serchText = serchText;
}
public int getSearchTextStartPosition() {
return searchTextStartPosition;
}
public void setSearchTextStartPosition(int searchTextStartPosition) {
this.searchTextStartPosition = searchTextStartPosition;
}
public int getSearchTextEndPosition() {
return searchTextEndPosition;
}
public void setSearchTextEndPosition(int searchTextEndPosition) {
this.searchTextEndPosition = searchTextEndPosition;
}
public SpannableString getSearchHighlightedSpan() {
return searchHighlightedSpan;
}
public void setSearchHighlightedSpan(SpannableString searchHighlightedSpan) {
this.searchHighlightedSpan = searchHighlightedSpan;
}
}
Raw
ArabicNormalizer.java
/**
* ArabicNormalizer class
* @author Ibrabel
*/
public final class ArabicNormalizer {
private String input;
private final String output;
/**
* ArabicNormalizer constructor
* @param input String
*/
public ArabicNormalizer(String input){
this.input=input;
this.output=normalize();
}
/**
* normalize Method
* @return String
*/
private String normalize(){
//Remove honorific sign
input=input.replaceAll("\u0610", "");//ARABIC SIGN SALLALLAHOU ALAYHE WA SALLAM
input=input.replaceAll("\u0611", "");//ARABIC SIGN ALAYHE ASSALLAM
input=input.replaceAll("\u0612", "");//ARABIC SIGN RAHMATULLAH ALAYHE
input=input.replaceAll("\u0613", "");//ARABIC SIGN RADI ALLAHOU ANHU
input=input.replaceAll("\u0614", "");//ARABIC SIGN TAKHALLUS
//Remove koranic anotation
input=input.replaceAll("\u0615", "");//ARABIC SMALL HIGH TAH
input=input.replaceAll("\u0616", "");//ARABIC SMALL HIGH LIGATURE ALEF WITH LAM WITH YEH
input=input.replaceAll("\u0617", "");//ARABIC SMALL HIGH ZAIN
input=input.replaceAll("\u0618", "");//ARABIC SMALL FATHA
input=input.replaceAll("\u0619", "");//ARABIC SMALL DAMMA
input=input.replaceAll("\u061A", "");//ARABIC SMALL KASRA
input=input.replaceAll("\u06D6", "");//ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA
input=input.replaceAll("\u06D7", "");//ARABIC SMALL HIGH LIGATURE QAF WITH LAM WITH ALEF MAKSURA
input=input.replaceAll("\u06D8", "");//ARABIC SMALL HIGH MEEM INITIAL FORM
input=input.replaceAll("\u06D9", "");//ARABIC SMALL HIGH LAM ALEF
input=input.replaceAll("\u06DA", "");//ARABIC SMALL HIGH JEEM
input=input.replaceAll("\u06DB", "");//ARABIC SMALL HIGH THREE DOTS
input=input.replaceAll("\u06DC", "");//ARABIC SMALL HIGH SEEN
input=input.replaceAll("\u06DD", "");//ARABIC END OF AYAH
input=input.replaceAll("\u06DE", "");//ARABIC START OF RUB EL HIZB
input=input.replaceAll("\u06DF", "");//ARABIC SMALL HIGH ROUNDED ZERO
input=input.replaceAll("\u06E0", "");//ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO
input=input.replaceAll("\u06E1", "");//ARABIC SMALL HIGH DOTLESS HEAD OF KHAH
input=input.replaceAll("\u06E2", "");//ARABIC SMALL HIGH MEEM ISOLATED FORM
input=input.replaceAll("\u06E3", "");//ARABIC SMALL LOW SEEN
input=input.replaceAll("\u06E4", "");//ARABIC SMALL HIGH MADDA
input=input.replaceAll("\u06E5", "");//ARABIC SMALL WAW
input=input.replaceAll("\u06E6", "");//ARABIC SMALL YEH
input=input.replaceAll("\u06E7", "");//ARABIC SMALL HIGH YEH
input=input.replaceAll("\u06E8", "");//ARABIC SMALL HIGH NOON
input=input.replaceAll("\u06E9", "");//ARABIC PLACE OF SAJDAH
input=input.replaceAll("\u06EA", "");//ARABIC EMPTY CENTRE LOW STOP
input=input.replaceAll("\u06EB", "");//ARABIC EMPTY CENTRE HIGH STOP
input=input.replaceAll("\u06EC", "");//ARABIC ROUNDED HIGH STOP WITH FILLED CENTRE
input=input.replaceAll("\u06ED", "");//ARABIC SMALL LOW MEEM
//Remove tatweel
input=input.replaceAll("\u0640", "");
//Remove tashkeel
input=input.replaceAll("\u064B", "");//ARABIC FATHATAN
input=input.replaceAll("\u064C", "");//ARABIC DAMMATAN
input=input.replaceAll("\u064D", "");//ARABIC KASRATAN
input=input.replaceAll("\u064E", "");//ARABIC FATHA
input=input.replaceAll("\u064F", "");//ARABIC DAMMA
input=input.replaceAll("\u0650", "");//ARABIC KASRA
input=input.replaceAll("\u0651", "");//ARABIC SHADDA
input=input.replaceAll("\u0652", "");//ARABIC SUKUN
input=input.replaceAll("\u0653", "");//ARABIC MADDAH ABOVE
input=input.replaceAll("\u0654", "");//ARABIC HAMZA ABOVE
input=input.replaceAll("\u0655", "");//ARABIC HAMZA BELOW
input=input.replaceAll("\u0656", "");//ARABIC SUBSCRIPT ALEF
input=input.replaceAll("\u0657", "");//ARABIC INVERTED DAMMA
input=input.replaceAll("\u0658", "");//ARABIC MARK NOON GHUNNA
input=input.replaceAll("\u0659", "");//ARABIC ZWARAKAY
input=input.replaceAll("\u065A", "");//ARABIC VOWEL SIGN SMALL V ABOVE
input=input.replaceAll("\u065B", "");//ARABIC VOWEL SIGN INVERTED SMALL V ABOVE
input=input.replaceAll("\u065C", "");//ARABIC VOWEL SIGN DOT BELOW
input=input.replaceAll("\u065D", "");//ARABIC REVERSED DAMMA
input=input.replaceAll("\u065E", "");//ARABIC FATHA WITH TWO DOTS
input=input.replaceAll("\u065F", "");//ARABIC WAVY HAMZA BELOW
input=input.replaceAll("\u0670", "");//ARABIC LETTER SUPERSCRIPT ALEF
//Replace Waw Hamza Above by Waw
input=input.replaceAll("\u0624", "\u0648");
//Replace Ta Marbuta by Ha
input=input.replaceAll("\u0629", "\u0647");
//Replace Ya
// and Ya Hamza Above by Alif Maksura
input=input.replaceAll("\u064A", "\u0649");
input=input.replaceAll("\u0626", "\u0649");
// Replace Alifs with Hamza Above/Below
// and with Madda Above by Alif
input=input.replaceAll("\u0622", "\u0627");
input=input.replaceAll("\u0623", "\u0627");
input=input.replaceAll("\u0625", "\u0627");
return input;
}
/**
* @return the output
*/
public String getOutput() {
return output;
}
public static void main(String[] args) {
String test = "كَلَّا لَا تُطِعْهُ وَاسْجُدْ وَاقْتَرِبْ ۩";
System.out.println("Before: "+test);
test=new ArabicNormalizer(test).getOutput();
System.out.println("After: "+test);
}
}
Raw
gistfile1.txt
SpannedString result = new SpannedString("");
for (int j=0;j<myString.length();j++){
Spannable wordtoSpan = new SpannableString(myString.substring(j,j+1));
if (arabicV.contains(myString.substring(j,j+1))) {
wordtoSpan.setSpan(new ForegroundColorSpan(Color.parseColor("#FF0000")),
0, 1, 0);
}
else
{
wordtoSpan.setSpan(new ForegroundColorSpan(Color.parseColor( "#000000")),
0, 1, 0);
}
result = (SpannedString) TextUtils.concat(result,"",wordtoSpan);
}
Raw
gistfile2.txt
ABHArabicDiacritics objSearchd = new ABHArabicDiacritics();
objSearchdobjSearch.getDiacriticinsensitive("وَ اَشْهَدُ اَنْ لا اِلهَ اِلاَّ اللَّهُ").contains("اشهد");
ABHArabicDiacritics objSearch = new ABHArabicDiacritics( وَ اَشْهَدُ اَنْ لا اِلهَ اِلاَّ اللَّهُ, اشهد);
SpannableString spoutput=objSearch.getSearchHighlightedSpan();
textView.setText(spoutput);
objSearch.isContain();//
objSearch.getSearchHighlightedSpan();
objSearch.getSearchTextStartPosition();
objSearch.getSearchTextEndPosition();
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment