X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicNormalizer.java
diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicNormalizer.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicNormalizer.java
new file mode 100644
index 0000000..c566176
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicNormalizer.java
@@ -0,0 +1,101 @@
+package org.apache.lucene.analysis.ar;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import static org.apache.lucene.analysis.util.StemmerUtil.*;
+
+/**
+ * Normalizer for Arabic.
+ *
+ * Normalization is done in-place for efficiency, operating on a termbuffer.
+ *
+ * Normalization is defined as:
+ *
+ * - Normalization of hamza with alef seat to a bare alef.
+ *
- Normalization of teh marbuta to heh
+ *
- Normalization of dotless yeh (alef maksura) to yeh.
+ *
- Removal of Arabic diacritics (the harakat)
+ *
- Removal of tatweel (stretching character).
+ *
+ *
+ */
+public class ArabicNormalizer {
+ public static final char ALEF = '\u0627';
+ public static final char ALEF_MADDA = '\u0622';
+ public static final char ALEF_HAMZA_ABOVE = '\u0623';
+ public static final char ALEF_HAMZA_BELOW = '\u0625';
+
+ public static final char YEH = '\u064A';
+ public static final char DOTLESS_YEH = '\u0649';
+
+ public static final char TEH_MARBUTA = '\u0629';
+ public static final char HEH = '\u0647';
+
+ public static final char TATWEEL = '\u0640';
+
+ public static final char FATHATAN = '\u064B';
+ public static final char DAMMATAN = '\u064C';
+ public static final char KASRATAN = '\u064D';
+ public static final char FATHA = '\u064E';
+ public static final char DAMMA = '\u064F';
+ public static final char KASRA = '\u0650';
+ public static final char SHADDA = '\u0651';
+ public static final char SUKUN = '\u0652';
+
+ /**
+ * Normalize an input buffer of Arabic text
+ *
+ * @param s input buffer
+ * @param len length of input buffer
+ * @return length of input buffer after normalization
+ */
+ public int normalize(char s[], int len) {
+
+ for (int i = 0; i < len; i++) {
+ switch (s[i]) {
+ case ALEF_MADDA:
+ case ALEF_HAMZA_ABOVE:
+ case ALEF_HAMZA_BELOW:
+ s[i] = ALEF;
+ break;
+ case DOTLESS_YEH:
+ s[i] = YEH;
+ break;
+ case TEH_MARBUTA:
+ s[i] = HEH;
+ break;
+ case TATWEEL:
+ case KASRATAN:
+ case DAMMATAN:
+ case FATHATAN:
+ case FATHA:
+ case DAMMA:
+ case KASRA:
+ case SHADDA:
+ case SUKUN:
+ len = delete(s, i, len);
+ i--;
+ break;
+ default:
+ break;
+ }
+ }
+
+ return len;
+ }
+}