1 |
torben |
2495 |
package dk.daoas.daoadresseservice.util; |
2 |
|
|
|
3 |
torben |
2531 |
import java.io.Serializable; |
4 |
|
|
|
5 |
torben |
2495 |
import java.util.Arrays; |
6 |
|
|
import java.util.Collections; |
7 |
|
|
import java.util.Comparator; |
8 |
|
|
import java.util.List; |
9 |
|
|
|
10 |
|
|
/* |
11 |
|
|
NaturalOrderComparator.java -- Perform 'natural order' comparisons of strings in Java. |
12 |
|
|
Copyright (C) 2003 by Pierre-Luc Paour <natorder@paour.com> |
13 |
|
|
|
14 |
|
|
Based on the C version by Martin Pool, of which this is more or less a straight conversion. |
15 |
|
|
Copyright (C) 2000 by Martin Pool <mbp@humbug.org.au> |
16 |
|
|
|
17 |
|
|
This software is provided 'as-is', without any express or implied |
18 |
|
|
warranty. In no event will the authors be held liable for any damages |
19 |
|
|
arising from the use of this software. |
20 |
|
|
|
21 |
|
|
Permission is granted to anyone to use this software for any purpose, |
22 |
|
|
including commercial applications, and to alter it and redistribute it |
23 |
|
|
freely, subject to the following restrictions: |
24 |
|
|
|
25 |
|
|
1. The origin of this software must not be misrepresented; you must not |
26 |
|
|
claim that you wrote the original software. If you use this software |
27 |
|
|
in a product, an acknowledgment in the product documentation would be |
28 |
|
|
appreciated but is not required. |
29 |
|
|
2. Altered source versions must be plainly marked as such, and must not be |
30 |
|
|
misrepresented as being the original software. |
31 |
|
|
3. This notice may not be removed or altered from any source distribution. |
32 |
|
|
*/ |
33 |
|
|
|
34 |
|
|
|
35 |
|
|
|
36 |
torben |
2531 |
public class NaturalOrderComparator<T> implements Comparator<T>, Serializable |
37 |
torben |
2495 |
{ |
38 |
|
|
int compareRight(String a, String b) |
39 |
|
|
{ |
40 |
|
|
int bias = 0; |
41 |
|
|
int ia = 0; |
42 |
|
|
int ib = 0; |
43 |
|
|
|
44 |
|
|
// The longest run of digits wins. That aside, the greatest |
45 |
|
|
// value wins, but we can't know that it will until we've scanned |
46 |
|
|
// both numbers to know that they have the same magnitude, so we |
47 |
|
|
// remember it in BIAS. |
48 |
|
|
for (;; ia++, ib++) |
49 |
|
|
{ |
50 |
|
|
char ca = charAt(a, ia); |
51 |
|
|
char cb = charAt(b, ib); |
52 |
|
|
|
53 |
|
|
if (!Character.isDigit(ca) && !Character.isDigit(cb)) |
54 |
|
|
{ |
55 |
|
|
return bias; |
56 |
|
|
} |
57 |
|
|
else if (!Character.isDigit(ca)) |
58 |
|
|
{ |
59 |
|
|
return -1; |
60 |
|
|
} |
61 |
|
|
else if (!Character.isDigit(cb)) |
62 |
|
|
{ |
63 |
|
|
return +1; |
64 |
|
|
} |
65 |
|
|
else if (ca < cb) |
66 |
|
|
{ |
67 |
|
|
if (bias == 0) |
68 |
|
|
{ |
69 |
|
|
bias = -1; |
70 |
|
|
} |
71 |
|
|
} |
72 |
|
|
else if (ca > cb) |
73 |
|
|
{ |
74 |
|
|
if (bias == 0) |
75 |
|
|
bias = +1; |
76 |
|
|
} |
77 |
|
|
else if (ca == 0 && cb == 0) |
78 |
|
|
{ |
79 |
|
|
return bias; |
80 |
|
|
} |
81 |
|
|
} |
82 |
|
|
} |
83 |
|
|
|
84 |
|
|
public int compare(T o1, T o2) |
85 |
|
|
{ |
86 |
|
|
String a = o1.toString(); |
87 |
|
|
String b = o2.toString(); |
88 |
|
|
|
89 |
|
|
int ia = 0, ib = 0; |
90 |
|
|
int nza = 0, nzb = 0; |
91 |
|
|
char ca, cb; |
92 |
|
|
int result; |
93 |
|
|
|
94 |
|
|
while (true) |
95 |
|
|
{ |
96 |
|
|
// only count the number of zeroes leading the last number compared |
97 |
|
|
nza = nzb = 0; |
98 |
|
|
|
99 |
|
|
ca = charAt(a, ia); |
100 |
|
|
cb = charAt(b, ib); |
101 |
|
|
|
102 |
|
|
// skip over leading spaces or zeros |
103 |
|
|
while (Character.isSpaceChar(ca) || ca == '0') |
104 |
|
|
{ |
105 |
|
|
if (ca == '0') |
106 |
|
|
{ |
107 |
|
|
nza++; |
108 |
|
|
} |
109 |
|
|
else |
110 |
|
|
{ |
111 |
|
|
// only count consecutive zeroes |
112 |
|
|
nza = 0; |
113 |
|
|
} |
114 |
|
|
|
115 |
|
|
ca = charAt(a, ++ia); |
116 |
|
|
} |
117 |
|
|
|
118 |
|
|
while (Character.isSpaceChar(cb) || cb == '0') |
119 |
|
|
{ |
120 |
|
|
if (cb == '0') |
121 |
|
|
{ |
122 |
|
|
nzb++; |
123 |
|
|
} |
124 |
|
|
else |
125 |
|
|
{ |
126 |
|
|
// only count consecutive zeroes |
127 |
|
|
nzb = 0; |
128 |
|
|
} |
129 |
|
|
|
130 |
|
|
cb = charAt(b, ++ib); |
131 |
|
|
} |
132 |
|
|
|
133 |
|
|
// process run of digits |
134 |
|
|
if (Character.isDigit(ca) && Character.isDigit(cb)) |
135 |
|
|
{ |
136 |
|
|
if ((result = compareRight(a.substring(ia), b.substring(ib))) != 0) |
137 |
|
|
{ |
138 |
|
|
return result; |
139 |
|
|
} |
140 |
|
|
} |
141 |
|
|
|
142 |
|
|
if (ca == 0 && cb == 0) |
143 |
|
|
{ |
144 |
|
|
// The strings compare the same. Perhaps the caller |
145 |
|
|
// will want to call strcmp to break the tie. |
146 |
|
|
return nza - nzb; |
147 |
|
|
} |
148 |
|
|
|
149 |
|
|
if (ca < cb) |
150 |
|
|
{ |
151 |
|
|
return -1; |
152 |
|
|
} |
153 |
|
|
else if (ca > cb) |
154 |
|
|
{ |
155 |
|
|
return +1; |
156 |
|
|
} |
157 |
|
|
|
158 |
|
|
++ia; |
159 |
|
|
++ib; |
160 |
|
|
} |
161 |
|
|
} |
162 |
|
|
|
163 |
|
|
static char charAt(String s, int i) |
164 |
|
|
{ |
165 |
|
|
if (i >= s.length()) |
166 |
|
|
{ |
167 |
|
|
return 0; |
168 |
|
|
} |
169 |
|
|
else |
170 |
|
|
{ |
171 |
|
|
return s.charAt(i); |
172 |
|
|
} |
173 |
|
|
} |
174 |
|
|
|
175 |
|
|
public static void main(String[] args) |
176 |
|
|
{ |
177 |
|
|
String[] strings = new String[] { "1-2", "1-02", "1-20", "10-20", "fred", "jane", "pic01", |
178 |
|
|
"pic2", "pic02", "pic02a", "pic3", "pic4", "pic 4 else", "pic 5", "pic05", "pic 5", |
179 |
|
|
"pic 5 something", "pic 6", "pic 7", "pic100", "pic100a", "pic120", "pic121", |
180 |
|
|
"pic02000", "tom", "x2-g8", "x2-y7", "x2-y08", "x8-y8" }; |
181 |
|
|
|
182 |
|
|
List orig = Arrays.asList(strings); |
183 |
|
|
|
184 |
|
|
System.out.println("Original: " + orig); |
185 |
|
|
|
186 |
|
|
List scrambled = Arrays.asList(strings); |
187 |
|
|
Collections.shuffle(scrambled); |
188 |
|
|
|
189 |
|
|
System.out.println("Scrambled: " + scrambled); |
190 |
|
|
|
191 |
|
|
Collections.sort(scrambled, new NaturalOrderComparator()); |
192 |
|
|
|
193 |
|
|
System.out.println("Sorted: " + scrambled); |
194 |
|
|
} |
195 |
torben |
2531 |
} |