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
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
|
/*
* Copyright (C) 2011 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.database.Cursor;
import android.database.sqlite.SQLiteDatabase;
import android.os.SystemClock;
import android.provider.ContactsContract.CommonDataKinds.Email;
import android.provider.ContactsContract.CommonDataKinds.Nickname;
import android.provider.ContactsContract.CommonDataKinds.Organization;
import android.provider.ContactsContract.CommonDataKinds.StructuredPostal;
import android.provider.ContactsContract.Data;
import android.provider.ContactsContract.ProviderStatus;
import android.provider.ContactsContract.RawContacts;
import android.text.TextUtils;
import android.util.Log;
import com.android.providers.contacts.ContactsDatabaseHelper.DataColumns;
import com.android.providers.contacts.ContactsDatabaseHelper.MimetypesColumns;
import com.android.providers.contacts.ContactsDatabaseHelper.RawContactsColumns;
import com.android.providers.contacts.ContactsDatabaseHelper.SearchIndexColumns;
import com.android.providers.contacts.ContactsDatabaseHelper.Tables;
import com.google.android.collect.Lists;
import com.google.common.annotations.VisibleForTesting;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.regex.Pattern;
/**
* Maintains a search index for comprehensive contact search.
*/
public class SearchIndexManager {
private static final String TAG = "ContactsFTS";
private static final boolean VERBOSE_LOGGING = Log.isLoggable(TAG, Log.VERBOSE);
public static final String PROPERTY_SEARCH_INDEX_VERSION = "search_index";
private static final int SEARCH_INDEX_VERSION = 1;
private static final class ContactIndexQuery {
public static final String[] COLUMNS = {
Data.CONTACT_ID,
MimetypesColumns.MIMETYPE,
Data.DATA1, Data.DATA2, Data.DATA3, Data.DATA4, Data.DATA5,
Data.DATA6, Data.DATA7, Data.DATA8, Data.DATA9, Data.DATA10, Data.DATA11,
Data.DATA12, Data.DATA13, Data.DATA14
};
public static final int MIMETYPE = 1;
}
public static class IndexBuilder {
public static final int SEPARATOR_SPACE = 0;
public static final int SEPARATOR_PARENTHESES = 1;
public static final int SEPARATOR_SLASH = 2;
public static final int SEPARATOR_COMMA = 3;
private StringBuilder mSbContent = new StringBuilder();
private StringBuilder mSbName = new StringBuilder();
private StringBuilder mSbTokens = new StringBuilder();
private StringBuilder mSbElementContent = new StringBuilder();
private HashSet<String> mUniqueElements = new HashSet<String>();
private Cursor mCursor;
void setCursor(Cursor cursor) {
this.mCursor = cursor;
}
void reset() {
mSbContent.setLength(0);
mSbTokens.setLength(0);
mSbName.setLength(0);
mSbElementContent.setLength(0);
mUniqueElements.clear();
}
public String getContent() {
return mSbContent.length() == 0 ? null : mSbContent.toString();
}
public String getName() {
return mSbName.length() == 0 ? null : mSbName.toString();
}
public String getTokens() {
return mSbTokens.length() == 0 ? null : mSbTokens.toString();
}
public String getString(String columnName) {
return mCursor.getString(mCursor.getColumnIndex(columnName));
}
public int getInt(String columnName) {
return mCursor.getInt(mCursor.getColumnIndex(columnName));
}
@Override
public String toString() {
return "Content: " + mSbContent + "\n Name: " + mSbTokens + "\n Tokens: " + mSbTokens;
}
public void commit() {
if (mSbElementContent.length() != 0) {
String content = mSbElementContent.toString().replace('\n', ' ');
if (!mUniqueElements.contains(content)) {
if (mSbContent.length() != 0) {
mSbContent.append('\n');
}
mSbContent.append(content);
mUniqueElements.add(content);
}
mSbElementContent.setLength(0);
}
}
public void appendContentFromColumn(String columnName) {
appendContentFromColumn(columnName, SEPARATOR_SPACE);
}
public void appendContentFromColumn(String columnName, int format) {
appendContent(getString(columnName), format);
}
public void appendContent(String value) {
appendContent(value, SEPARATOR_SPACE);
}
private void appendContent(String value, int format) {
if (TextUtils.isEmpty(value)) {
return;
}
switch (format) {
case SEPARATOR_SPACE:
if (mSbElementContent.length() > 0) {
mSbElementContent.append(' ');
}
mSbElementContent.append(value);
break;
case SEPARATOR_SLASH:
mSbElementContent.append('/').append(value);
break;
case SEPARATOR_PARENTHESES:
if (mSbElementContent.length() > 0) {
mSbElementContent.append(' ');
}
mSbElementContent.append('(').append(value).append(')');
break;
case SEPARATOR_COMMA:
if (mSbElementContent.length() > 0) {
mSbElementContent.append(", ");
}
mSbElementContent.append(value);
break;
}
}
public void appendToken(String token) {
if (TextUtils.isEmpty(token)) {
return;
}
if (mSbTokens.length() != 0) {
mSbTokens.append(' ');
}
mSbTokens.append(token);
}
public void appendName(String name) {
if (TextUtils.isEmpty(name)) {
return;
}
// First, put the original name.
appendNameInternal(name);
// Then, if the name contains more than one FTS token, put each token into the index
// too.
//
// This is to make names with special characters searchable, such as "double-barrelled"
// "L'Image".
//
// Here's how it works:
// Because we "normalize" names when putting into the index, if we only put
// "double-barrelled", the index will only contain "doublebarrelled".
// Now, if the user searches for "double-barrelled", the searcher tokenizes it into
// two tokens, "double" and "barrelled". The first one matches "doublebarrelled"
// but the second one doesn't (because we only do the prefix match), so
// "doublebarrelled" doesn't match.
// So, here, we put each token in a name into the index too. In the case above,
// we put also "double" and "barrelled".
// With this, queries such as "double-barrelled", "double barrelled", "doublebarrelled"
// will all match "double-barrelled".
final List<String> nameParts = splitIntoFtsTokens(name);
if (nameParts.size() > 1) {
for (String namePart : nameParts) {
if (!TextUtils.isEmpty(namePart)) {
appendNameInternal(namePart);
}
}
}
}
/**
* Normalize a name and add to {@link #mSbName}
*/
private void appendNameInternal(String name) {
if (mSbName.length() != 0) {
mSbName.append(' ');
}
mSbName.append(NameNormalizer.normalize(name));
}
}
private final ContactsProvider2 mContactsProvider;
private final ContactsDatabaseHelper mDbHelper;
private StringBuilder mSb = new StringBuilder();
private IndexBuilder mIndexBuilder = new IndexBuilder();
private ContentValues mValues = new ContentValues();
private String[] mSelectionArgs1 = new String[1];
public SearchIndexManager(ContactsProvider2 contactsProvider) {
this.mContactsProvider = contactsProvider;
mDbHelper = (ContactsDatabaseHelper) mContactsProvider.getDatabaseHelper();
}
public void updateIndex() {
if (getSearchIndexVersion() == SEARCH_INDEX_VERSION) {
return;
}
SQLiteDatabase db = mDbHelper.getWritableDatabase();
db.beginTransaction();
try {
if (getSearchIndexVersion() != SEARCH_INDEX_VERSION) {
rebuildIndex(db);
setSearchIndexVersion(SEARCH_INDEX_VERSION);
db.setTransactionSuccessful();
}
} finally {
db.endTransaction();
}
}
private void rebuildIndex(SQLiteDatabase db) {
mContactsProvider.setProviderStatus(ProviderStatus.STATUS_UPGRADING);
final long start = SystemClock.elapsedRealtime();
int count = 0;
try {
mDbHelper.createSearchIndexTable(db);
count = buildAndInsertIndex(db, null);
} finally {
mContactsProvider.setProviderStatus(ProviderStatus.STATUS_NORMAL);
final long end = SystemClock.elapsedRealtime();
Log.i(TAG, "Rebuild contact search index in " + (end - start) + "ms, "
+ count + " contacts");
}
}
public void updateIndexForRawContacts(Set<Long> contactIds, Set<Long> rawContactIds) {
if (VERBOSE_LOGGING) {
Log.v(TAG, "Updating search index for " + contactIds.size() +
" contacts / " + rawContactIds.size() + " raw contacts");
}
StringBuilder sb = new StringBuilder();
sb.append("(");
if (!contactIds.isEmpty()) {
sb.append(RawContacts.CONTACT_ID + " IN (");
for (Long contactId : contactIds) {
sb.append(contactId).append(",");
}
sb.setLength(sb.length() - 1);
sb.append(')');
}
if (!rawContactIds.isEmpty()) {
if (!contactIds.isEmpty()) {
sb.append(" OR ");
}
sb.append(RawContactsColumns.CONCRETE_ID + " IN (");
for (Long rawContactId : rawContactIds) {
sb.append(rawContactId).append(",");
}
sb.setLength(sb.length() - 1);
sb.append(')');
}
sb.append(")");
// The selection to select raw_contacts.
final String rawContactsSelection = sb.toString();
// Remove affected search_index rows.
final SQLiteDatabase db = mDbHelper.getWritableDatabase();
final int deleted = db.delete(Tables.SEARCH_INDEX,
SearchIndexColumns.CONTACT_ID + " IN (SELECT " +
RawContacts.CONTACT_ID +
" FROM " + Tables.RAW_CONTACTS +
" WHERE " + rawContactsSelection +
")"
, null);
// Then rebuild index for them.
final int count = buildAndInsertIndex(db, rawContactsSelection);
if (VERBOSE_LOGGING) {
Log.v(TAG, "Updated search index for " + count + " contacts");
}
}
private int buildAndInsertIndex(SQLiteDatabase db, String selection) {
mSb.setLength(0);
mSb.append(Data.CONTACT_ID + ", ");
mSb.append("(CASE WHEN " + DataColumns.MIMETYPE_ID + "=");
mSb.append(mDbHelper.getMimeTypeId(Nickname.CONTENT_ITEM_TYPE));
mSb.append(" THEN -4 ");
mSb.append(" WHEN " + DataColumns.MIMETYPE_ID + "=");
mSb.append(mDbHelper.getMimeTypeId(Organization.CONTENT_ITEM_TYPE));
mSb.append(" THEN -3 ");
mSb.append(" WHEN " + DataColumns.MIMETYPE_ID + "=");
mSb.append(mDbHelper.getMimeTypeId(StructuredPostal.CONTENT_ITEM_TYPE));
mSb.append(" THEN -2");
mSb.append(" WHEN " + DataColumns.MIMETYPE_ID + "=");
mSb.append(mDbHelper.getMimeTypeId(Email.CONTENT_ITEM_TYPE));
mSb.append(" THEN -1");
mSb.append(" ELSE " + DataColumns.MIMETYPE_ID);
mSb.append(" END), " + Data.IS_SUPER_PRIMARY + ", " + DataColumns.CONCRETE_ID);
int count = 0;
Cursor cursor = db.query(Tables.DATA_JOIN_MIMETYPE_RAW_CONTACTS, ContactIndexQuery.COLUMNS,
selection, null, null, null, mSb.toString());
mIndexBuilder.setCursor(cursor);
mIndexBuilder.reset();
try {
long currentContactId = -1;
while (cursor.moveToNext()) {
long contactId = cursor.getLong(0);
if (contactId != currentContactId) {
if (currentContactId != -1) {
insertIndexRow(db, currentContactId, mIndexBuilder);
count++;
}
currentContactId = contactId;
mIndexBuilder.reset();
}
String mimetype = cursor.getString(ContactIndexQuery.MIMETYPE);
DataRowHandler dataRowHandler = mContactsProvider.getDataRowHandler(mimetype);
if (dataRowHandler.hasSearchableData()) {
dataRowHandler.appendSearchableData(mIndexBuilder);
mIndexBuilder.commit();
}
}
if (currentContactId != -1) {
insertIndexRow(db, currentContactId, mIndexBuilder);
count++;
}
} finally {
cursor.close();
}
return count;
}
private void insertIndexRow(SQLiteDatabase db, long contactId, IndexBuilder builder) {
mValues.clear();
mValues.put(SearchIndexColumns.CONTENT, builder.getContent());
mValues.put(SearchIndexColumns.NAME, builder.getName());
mValues.put(SearchIndexColumns.TOKENS, builder.getTokens());
mValues.put(SearchIndexColumns.CONTACT_ID, contactId);
db.insert(Tables.SEARCH_INDEX, null, mValues);
}
private int getSearchIndexVersion() {
return Integer.parseInt(mDbHelper.getProperty(PROPERTY_SEARCH_INDEX_VERSION, "0"));
}
private void setSearchIndexVersion(int version) {
mDbHelper.setProperty(PROPERTY_SEARCH_INDEX_VERSION, String.valueOf(version));
}
/**
* Token separator that matches SQLite's "simple" tokenizer.
* - Unicode codepoints >= 128: Everything
* - Unicode codepoints < 128: Alphanumeric and "_"
* - Everything else is a separator of tokens
*/
private static final Pattern FTS_TOKEN_SEPARATOR_RE =
Pattern.compile("[^\u0080-\uffff\\p{Alnum}_]");
/**
* Tokenize a string in the way as that of SQLite's "simple" tokenizer.
*/
@VisibleForTesting
static List<String> splitIntoFtsTokens(String s) {
final ArrayList<String> ret = Lists.newArrayList();
for (String token : FTS_TOKEN_SEPARATOR_RE.split(s)) {
if (!TextUtils.isEmpty(token)) {
ret.add(token);
}
}
return ret;
}
/**
* Tokenizes the query and normalizes/hex encodes each token. The tokenizer uses the same
* rules as SQLite's "simple" tokenizer. Each token is added to the retokenizer and then
* returned as a String.
* @see FtsQueryBuilder#UNSCOPED_NORMALIZING
* @see FtsQueryBuilder#SCOPED_NAME_NORMALIZING
*/
public static String getFtsMatchQuery(String query, FtsQueryBuilder ftsQueryBuilder) {
final StringBuilder result = new StringBuilder();
for (String token : splitIntoFtsTokens(query)) {
ftsQueryBuilder.addToken(result, token);
}
return result.toString();
}
public static abstract class FtsQueryBuilder {
public abstract void addToken(StringBuilder builder, String token);
/** Normalizes and space-concatenates each token. Example: "a1b2c1* a2b3c2*" */
public static final FtsQueryBuilder UNSCOPED_NORMALIZING = new UnscopedNormalizingBuilder();
/**
* Scopes each token to a column and normalizes the name.
* Example: "content:foo* name:a1b2c1* tokens:foo* content:bar* name:a2b3c2* tokens:bar*"
*/
public static final FtsQueryBuilder SCOPED_NAME_NORMALIZING =
new ScopedNameNormalizingBuilder();
/**
* Scopes each token to a the content column and also for name with normalization.
* Also adds a user-defined expression to each token. This allows common criteria to be
* concatenated to each token.
* Example (commonCriteria=" OR tokens:123*"):
* "content:650* OR name:1A1B1C* OR tokens:123* content:2A2B2C* OR name:foo* OR tokens:123*"
*/
public static FtsQueryBuilder getDigitsQueryBuilder(final String commonCriteria) {
return new FtsQueryBuilder() {
@Override
public void addToken(StringBuilder builder, String token) {
if (builder.length() != 0) builder.append(' ');
builder.append("content:");
builder.append(token);
builder.append("* ");
final String normalizedToken = NameNormalizer.normalize(token);
if (!TextUtils.isEmpty(normalizedToken)) {
builder.append(" OR name:");
builder.append(normalizedToken);
builder.append('*');
}
builder.append(commonCriteria);
}
};
}
}
private static class UnscopedNormalizingBuilder extends FtsQueryBuilder {
@Override
public void addToken(StringBuilder builder, String token) {
if (builder.length() != 0) builder.append(' ');
// the token could be empty (if the search query was "_"). we should still emit it
// here, as we otherwise risk to end up with an empty MATCH-expression MATCH ""
builder.append(NameNormalizer.normalize(token));
builder.append('*');
}
}
private static class ScopedNameNormalizingBuilder extends FtsQueryBuilder {
@Override
public void addToken(StringBuilder builder, String token) {
if (builder.length() != 0) builder.append(' ');
builder.append("content:");
builder.append(token);
builder.append('*');
final String normalizedToken = NameNormalizer.normalize(token);
if (!TextUtils.isEmpty(normalizedToken)) {
builder.append(" OR name:");
builder.append(normalizedToken);
builder.append('*');
}
builder.append(" OR tokens:");
builder.append(token);
builder.append("*");
}
}
}
|