1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
|
/*
* Copyright (C) 2009 The Android Open Source Project
*
* Licensed 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
*/
package com.android.providers.contacts;
import android.content.ContentValues;
import android.provider.ContactsContract.CommonDataKinds.StructuredName;
import android.text.TextUtils;
import java.util.HashSet;
import java.util.Locale;
import java.util.StringTokenizer;
/**
* The purpose of this class is to split a full name into given names and last
* name. The logic only supports having a single last name. If the full name has
* multiple last names the output will be incorrect.
* <p>
* Core algorithm:
* <ol>
* <li>Remove the suffixes (III, Ph.D., M.D.).</li>
* <li>Remove the prefixes (Mr., Pastor, Reverend, Sir).</li>
* <li>Assign the last remaining token as the last name.</li>
* <li>If the previous word to the last name is one from LASTNAME_PREFIXES, use
* this word also as the last name.</li>
* <li>Assign the rest of the words as the "given names".</li>
* </ol>
*/
public class NameSplitter {
public static final int MAX_TOKENS = 10;
private final HashSet<String> mPrefixesSet;
private final HashSet<String> mSuffixesSet;
private final int mMaxSuffixLength;
private final HashSet<String> mLastNamePrefixesSet;
private final HashSet<String> mConjuctions;
private final Locale mLocale;
public static class Name {
private String prefix;
private String givenNames;
private String middleName;
private String familyName;
private String suffix;
public Name() {
}
public Name(String prefix, String givenNames, String middleName, String familyName,
String suffix) {
this.prefix = prefix;
this.givenNames = givenNames;
this.middleName = middleName;
this.familyName = familyName;
this.suffix = suffix;
}
public String getPrefix() {
return prefix;
}
public String getGivenNames() {
return givenNames;
}
public String getMiddleName() {
return middleName;
}
public String getFamilyName() {
return familyName;
}
public String getSuffix() {
return suffix;
}
public void fromValues(ContentValues values) {
prefix = values.getAsString(StructuredName.PREFIX);
givenNames = values.getAsString(StructuredName.GIVEN_NAME);
middleName = values.getAsString(StructuredName.MIDDLE_NAME);
familyName = values.getAsString(StructuredName.FAMILY_NAME);
suffix = values.getAsString(StructuredName.SUFFIX);
}
public void toValues(ContentValues values) {
values.put(StructuredName.PREFIX, prefix);
values.put(StructuredName.GIVEN_NAME, givenNames);
values.put(StructuredName.MIDDLE_NAME, middleName);
values.put(StructuredName.FAMILY_NAME, familyName);
values.put(StructuredName.SUFFIX, suffix);
}
}
private static class NameTokenizer extends StringTokenizer {
private final String[] mTokens;
private int mDotBitmask;
private int mStartPointer;
private int mEndPointer;
public NameTokenizer(String fullName) {
super(fullName, " .,", true);
mTokens = new String[MAX_TOKENS];
// Iterate over tokens, skipping over empty ones and marking tokens that
// are followed by dots.
while (hasMoreTokens() && mEndPointer < MAX_TOKENS) {
final String token = nextToken();
if (token.length() > 0) {
final char c = token.charAt(0);
if (c == ' ' || c == ',') {
continue;
}
}
if (mEndPointer > 0 && token.charAt(0) == '.') {
mDotBitmask |= (1 << (mEndPointer - 1));
} else {
mTokens[mEndPointer] = token;
mEndPointer++;
}
}
}
/**
* Returns true if the token is followed by a dot in the original full name.
*/
public boolean hasDot(int index) {
return (mDotBitmask & (1 << index)) != 0;
}
}
/**
* Constructor.
*
* @param commonPrefixes comma-separated list of common prefixes,
* e.g. "Mr, Ms, Mrs"
* @param commonLastNamePrefixes comma-separated list of common last name prefixes,
* e.g. "d', st, st., von"
* @param commonSuffixes comma-separated list of common suffixes,
* e.g. "Jr, M.D., MD, D.D.S."
* @param commonConjunctions comma-separated list of common conjuctions,
* e.g. "AND, Or"
*/
public NameSplitter(String commonPrefixes, String commonLastNamePrefixes,
String commonSuffixes, String commonConjunctions, Locale locale) {
// TODO: refactor this to use <string-array> resources
mPrefixesSet = convertToSet(commonPrefixes);
mLastNamePrefixesSet = convertToSet(commonLastNamePrefixes);
mSuffixesSet = convertToSet(commonSuffixes);
mConjuctions = convertToSet(commonConjunctions);
mLocale = locale;
int maxLength = 0;
for (String suffix : mSuffixesSet) {
if (suffix.length() > maxLength) {
maxLength = suffix.length();
}
}
mMaxSuffixLength = maxLength;
}
/**
* Converts a comma-separated list of Strings to a set of Strings. Trims strings
* and converts them to upper case.
*/
private static HashSet<String> convertToSet(String strings) {
HashSet<String> set = new HashSet<String>();
if (strings != null) {
String[] split = strings.split(",");
for (int i = 0; i < split.length; i++) {
set.add(split[i].trim().toUpperCase());
}
}
return set;
}
/**
* Parses a full name and returns components as a list of tokens.
*/
public int tokenize(String[] tokens, String fullName) {
if (fullName == null) {
return 0;
}
NameTokenizer tokenizer = new NameTokenizer(fullName);
if (tokenizer.mStartPointer == tokenizer.mEndPointer) {
return 0;
}
String firstToken = tokenizer.mTokens[tokenizer.mStartPointer];
if (mPrefixesSet.contains(firstToken.toUpperCase())) {
tokenizer.mStartPointer++;
}
int count = 0;
for (int i = tokenizer.mStartPointer; i < tokenizer.mEndPointer; i++) {
tokens[count++] = tokenizer.mTokens[i];
}
return count;
}
/**
* Parses a full name and returns parsed components in the Name object.
*/
public void split(Name name, String fullName) {
if (fullName == null) {
return;
}
NameTokenizer tokens = new NameTokenizer(fullName);
parsePrefix(name, tokens);
// If the name consists of just one or two tokens, treat them as first/last name,
// not as suffix. Example: John Ma; Ma is last name, not "M.A.".
if (tokens.mEndPointer > 2) {
parseSuffix(name, tokens);
}
if (name.prefix == null && tokens.mEndPointer - tokens.mStartPointer == 1) {
name.givenNames = tokens.mTokens[tokens.mStartPointer];
} else {
parseLastName(name, tokens);
parseMiddleName(name, tokens);
parseGivenNames(name, tokens);
}
}
/**
* Flattens the given {@link Name} into a single field, usually for storage
* in {@link StructuredName#DISPLAY_NAME}.
*/
public String join(Name name) {
final boolean hasGiven = !TextUtils.isEmpty(name.givenNames);
final boolean hasFamily = !TextUtils.isEmpty(name.familyName);
// TODO: write locale-specific blending logic here
if (hasGiven && hasFamily) {
return name.givenNames + " " + name.familyName;
} else if (hasFamily) {
return name.familyName;
} else if (hasGiven) {
return name.givenNames;
} else {
return null;
}
}
/**
* Parses the first word from the name if it is a prefix.
*/
private void parsePrefix(Name name, NameTokenizer tokens) {
if (tokens.mStartPointer == tokens.mEndPointer) {
return;
}
String firstToken = tokens.mTokens[tokens.mStartPointer];
if (mPrefixesSet.contains(firstToken.toUpperCase())) {
name.prefix = firstToken;
tokens.mStartPointer++;
}
}
/**
* Parses the last word(s) from the name if it is a suffix.
*/
private void parseSuffix(Name name, NameTokenizer tokens) {
if (tokens.mStartPointer == tokens.mEndPointer) {
return;
}
String lastToken = tokens.mTokens[tokens.mEndPointer - 1];
if (lastToken.length() > mMaxSuffixLength) {
return;
}
String normalized = lastToken.toUpperCase();
if (mSuffixesSet.contains(normalized)) {
name.suffix = lastToken;
tokens.mEndPointer--;
return;
}
if (tokens.hasDot(tokens.mEndPointer - 1)) {
lastToken += '.';
}
normalized += ".";
// Take care of suffixes like M.D. and D.D.S.
int pos = tokens.mEndPointer - 1;
while (normalized.length() <= mMaxSuffixLength) {
if (mSuffixesSet.contains(normalized)) {
name.suffix = lastToken;
tokens.mEndPointer = pos;
return;
}
if (pos == tokens.mStartPointer) {
break;
}
pos--;
if (tokens.hasDot(pos)) {
lastToken = tokens.mTokens[pos] + "." + lastToken;
} else {
lastToken = tokens.mTokens[pos] + " " + lastToken;
}
normalized = tokens.mTokens[pos].toUpperCase() + "." + normalized;
}
}
private void parseLastName(Name name, NameTokenizer tokens) {
if (tokens.mStartPointer == tokens.mEndPointer) {
return;
}
name.familyName = tokens.mTokens[tokens.mEndPointer - 1];
tokens.mEndPointer--;
// Take care of last names like "D'Onofrio" and "von Cliburn"
if ((tokens.mEndPointer - tokens.mStartPointer) > 0) {
String lastNamePrefix = tokens.mTokens[tokens.mEndPointer - 1];
final String normalized = lastNamePrefix.toUpperCase();
if (mLastNamePrefixesSet.contains(normalized)
|| mLastNamePrefixesSet.contains(normalized + ".")) {
if (tokens.hasDot(tokens.mEndPointer - 1)) {
lastNamePrefix += '.';
}
name.familyName = lastNamePrefix + " " + name.familyName;
tokens.mEndPointer--;
}
}
}
private void parseMiddleName(Name name, NameTokenizer tokens) {
if (tokens.mStartPointer == tokens.mEndPointer) {
return;
}
if ((tokens.mEndPointer - tokens.mStartPointer) > 1) {
if ((tokens.mEndPointer - tokens.mStartPointer) == 2
|| !mConjuctions.contains(tokens.mTokens[tokens.mEndPointer - 2].
toUpperCase())) {
name.middleName = tokens.mTokens[tokens.mEndPointer - 1];
tokens.mEndPointer--;
}
}
}
private void parseGivenNames(Name name, NameTokenizer tokens) {
if (tokens.mStartPointer == tokens.mEndPointer) {
return;
}
if ((tokens.mEndPointer - tokens.mStartPointer) == 1) {
name.givenNames = tokens.mTokens[tokens.mStartPointer];
} else {
StringBuilder sb = new StringBuilder();
for (int i = tokens.mStartPointer; i < tokens.mEndPointer; i++) {
if (i != tokens.mStartPointer) {
sb.append(' ');
}
sb.append(tokens.mTokens[i]);
if (tokens.hasDot(i)) {
sb.append('.');
}
}
name.givenNames = sb.toString();
}
}
}
|