getGlyphSubstitutionMap() {
+ return glyphSubstitutionMap;
+ }
+
}
Index: src/main/java/com/itextpdf/text/pdf/languages/IndicCompositeCharacterComparator.java
===================================================================
--- src/main/java/com/itextpdf/text/pdf/languages/IndicCompositeCharacterComparator.java (revision 0)
+++ src/main/java/com/itextpdf/text/pdf/languages/IndicCompositeCharacterComparator.java (working copy)
@@ -0,0 +1,39 @@
+package com.itextpdf.text.pdf.languages;
+
+import java.util.Comparator;
+
+/**
+ *
+ * This works on CompositeCharcaters or Juktakshar-s of Indian languages like Bangla, Hindi, etc. CompositeCharcters
+ * are single glyphs consisting of more than one characters.
+ *
+ *
+ * This class works on these CompositeCharacters and places the Strings having higher number
+ * of Characters before the one with lower no. This is necessay to properly display the CompositeCharacters
+ * when they occur side by side.
+ *
+ *
+ *
Examples of CompositeCharactes from Bangla
+ *
+ * - ঙ্গ
+ * - ঙ্
+ * - ক্ষ্ম
+ * - ক্ষ
+ *
+ *
+ *
+ * @author Palash Ray
+ */
+public class IndicCompositeCharacterComparator implements Comparator {
+
+ public int compare(String o1, String o2) {
+ if (o2.length() > o1.length()) {
+ return 1;
+ } else if (o1.length() > o2.length()) {
+ return -1;
+ } else {
+ return o1.compareTo(o2);
+ }
+ }
+
+}
Index: src/test/java/com/itextpdf/text/pdf/ArrayBasedStringTokenizerTest.java
===================================================================
--- src/test/java/com/itextpdf/text/pdf/ArrayBasedStringTokenizerTest.java (revision 0)
+++ src/test/java/com/itextpdf/text/pdf/ArrayBasedStringTokenizerTest.java (working copy)
@@ -0,0 +1,102 @@
+package com.itextpdf.text.pdf;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
+import java.util.Arrays;
+import java.util.List;
+
+import org.junit.Test;
+
+/**
+ *
+ * @author Palash Ray
+ */
+public class ArrayBasedStringTokenizerTest {
+
+ @Test
+ public void testTokenize_happyPath() {
+ //given
+ ArrayBasedStringTokenizer tokenizer = new ArrayBasedStringTokenizer(new String[]{"aZx", "b2c", "bc2"});
+ String text = "12345aZxxabbccb2cxxxcfb1245678bc2889000";
+
+ //when
+ List tokens = Arrays.asList(tokenizer.tokenize(text));
+
+ //then
+ StringBuilder sb = new StringBuilder();
+ for (String token : tokens) {
+ sb.append(token);
+ }
+
+ assertEquals(text, sb.toString());
+ assertEquals(tokens, Arrays.asList("12345", "aZx", "xabbcc", "b2c", "xxxcfb1245678", "bc2", "889000"));
+ }
+
+ @Test
+ public void testTokenize_regexAtStart() {
+ //given
+ ArrayBasedStringTokenizer tokenizer = new ArrayBasedStringTokenizer(new String[]{"aZx", "b2c", "bc2"});
+ String text = "bc2e12345aZxxabbccb2cxxxcfb1245678bc2889000";
+
+ //when
+ String[] tokens = tokenizer.tokenize(text);
+
+ //then
+ StringBuilder sb = new StringBuilder();
+ for (String token : tokens) {
+ sb.append(token);
+ }
+
+ assertEquals(text, sb.toString());
+
+ List tokenList = Arrays.asList(tokens);
+
+ assertEquals(0, tokenList.indexOf("bc2"));
+ }
+
+ @Test
+ public void testTokenize_regexAtEnd() {
+ //given
+ ArrayBasedStringTokenizer tokenizer = new ArrayBasedStringTokenizer(new String[]{"aZx", "b2c", "bc2"});
+ String text = "bc2e12345aZxxabbccb2cxxxcfb1245678bc2889000aZx";
+
+ //when
+ List tokens = Arrays.asList(tokenizer.tokenize(text));
+
+ //then
+ StringBuilder sb = new StringBuilder();
+ for (String token : tokens) {
+ sb.append(token);
+ }
+
+ assertEquals(text, sb.toString());
+ assertEquals(0, tokens.indexOf("bc2"));
+ assertEquals(2, tokens.indexOf("aZx"));
+ assertEquals(tokens.size() - 1, tokens.lastIndexOf("aZx"));
+ }
+
+ @Test
+ public void testTokenize_Bangla() {
+ //given
+ ArrayBasedStringTokenizer tokenizer = new ArrayBasedStringTokenizer(new String[]{"\u0995\u09cd\u09b7", "পু"});
+ String text = "আমি কোন পথে ক্ষীরের ষন্ড পুতুল রুপো গঙ্গা ঋষি";
+
+ //when
+ String[] tokens = tokenizer.tokenize(text);
+
+ //then
+ StringBuilder sb = new StringBuilder();
+ for (String token : tokens) {
+ sb.append(token);
+ }
+
+ assertEquals(text, sb.toString());
+
+ List tokenList = Arrays.asList(tokens);
+
+ assertTrue(tokenList.contains("ক্ষ"));
+ assertTrue(tokenList.contains("পু"));
+ }
+
+}