001: /*
002: * The Apache Software License, Version 1.1
003: *
004: *
005: * Copyright (c) 1999 The Apache Software Foundation. All rights
006: * reserved.
007: *
008: * Redistribution and use in source and binary forms, with or without
009: * modification, are permitted provided that the following conditions
010: * are met:
011: *
012: * 1. Redistributions of source code must retain the above copyright
013: * notice, this list of conditions and the following disclaimer.
014: *
015: * 2. Redistributions in binary form must reproduce the above copyright
016: * notice, this list of conditions and the following disclaimer in
017: * the documentation and/or other materials provided with the
018: * distribution.
019: *
020: * 3. The end-user documentation included with the redistribution,
021: * if any, must include the following acknowledgment:
022: * "This product includes software developed by the
023: * Apache Software Foundation (http://www.apache.org/)."
024: * Alternately, this acknowledgment may appear in the software itself,
025: * if and wherever such third-party acknowledgments normally appear.
026: *
027: * 4. The names "Xerces" and "Apache Software Foundation" must
028: * not be used to endorse or promote products derived from this
029: * software without prior written permission. For written
030: * permission, please contact apache@apache.org.
031: *
032: * 5. Products derived from this software may not be called "Apache",
033: * nor may "Apache" appear in their name, without prior written
034: * permission of the Apache Software Foundation.
035: *
036: * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
037: * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
038: * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
039: * DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
040: * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
041: * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
042: * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
043: * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
044: * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
045: * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
046: * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
047: * SUCH DAMAGE.
048: * ====================================================================
049: *
050: * This software consists of voluntary contributions made by many
051: * individuals on behalf of the Apache Software Foundation and was
052: * originally based on software copyright (c) 1999, International
053: * Business Machines, Inc., http://www.apache.org. For more
054: * information on the Apache Software Foundation, please see
055: * <http://www.apache.org/>.
056: */
057:
058: package org.apache.xerces.utils;
059:
060: /**
061: * Algorithm used to hash char arrays (strings).
062: *
063: * This class was created after it was discovered that parsing some
064: * documents was unexpectedly slow due to many different strings
065: * hashing to the same 32-bit value using the java.lang.String hash
066: * algorithm.
067: *
068: * The trick seems to be the shift of the top eight bits of the hashcode
069: * back down to the bottom to keep them from being rolled out.
070: *
071: * @version
072: */
073: public final class StringHasher {
074: /**
075: * generate a hashcode for a String
076: *
077: * @param str the String to hash
078: * @param strLength the length of the String to hash
079: * @return hashcode for the String
080: */
081: public static int hashString(String str, int strLength) {
082: int hashcode = 0;
083: for (int i = 0; i < strLength; i++) {
084: int top = hashcode >> 24;
085: hashcode += ((hashcode * 37) + top + ((int) str.charAt(i)));
086: }
087: hashcode = (hashcode & 0x7fffffff);
088: return (hashcode == 0) ? 1 : hashcode;
089: }
090:
091: /**
092: * generate a hashcode for a character array
093: *
094: * @param chars the array to hash
095: * @param offset the offset to start hashing
096: * @param length the length of characters to hash
097: * @return hashcode for the character array
098: */
099: public static int hashChars(char[] chars, int offset, int length) {
100: int hashcode = 0;
101: for (int i = 0; i < length; i++) {
102: int top = hashcode >> 24;
103: hashcode += ((hashcode * 37) + top + ((int) (chars[offset++] & 0xFFFF)));
104: }
105: hashcode = (hashcode & 0x7fffffff);
106: return (hashcode == 0) ? 1 : hashcode;
107: }
108:
109: /**
110: * generate partially completed character hashcode.
111: * this is mean to be iterated over individual characters in order to generate
112: * a full hash value
113: * @see #finishHash(int)
114: *
115: * @param hashcode a partially completed character hashcode
116: * @param ch the character to hash
117: * @return a partially completed character hashcode
118: */
119: public static int hashChar(int hashcode, int ch) {
120: int top = hashcode >> 24;
121: hashcode += ((hashcode * 37) + top + ch);
122: return hashcode;
123: }
124:
125: /**
126: * finish hashing a partically completed character hashcode
127: * @see #hashChar(int,int)
128: *
129: * @param hashcode a partially completed character hashcode
130: * @return a character hashcode
131: */
132: public static int finishHash(int hashcode) {
133: hashcode = (hashcode & 0x7fffffff);
134: return (hashcode == 0) ? 1 : hashcode;
135: }
136: }
|