1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/** |
4
|
|
|
* webtrees: online genealogy |
5
|
|
|
* Copyright (C) 2019 webtrees development team |
6
|
|
|
* This program is free software: you can redistribute it and/or modify |
7
|
|
|
* it under the terms of the GNU General Public License as published by |
8
|
|
|
* the Free Software Foundation, either version 3 of the License, or |
9
|
|
|
* (at your option) any later version. |
10
|
|
|
* This program is distributed in the hope that it will be useful, |
11
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
12
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
13
|
|
|
* GNU General Public License for more details. |
14
|
|
|
* You should have received a copy of the GNU General Public License |
15
|
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>. |
16
|
|
|
*/ |
17
|
|
|
|
18
|
|
|
declare(strict_types=1); |
19
|
|
|
|
20
|
|
|
namespace Fisharebest\Webtrees\Module; |
21
|
|
|
|
22
|
|
|
use Fisharebest\Webtrees\Exceptions\HttpNotFoundException; |
23
|
|
|
use Fisharebest\Webtrees\Family; |
24
|
|
|
use Fisharebest\Webtrees\GedcomRecord; |
25
|
|
|
use Fisharebest\Webtrees\I18N; |
26
|
|
|
use Fisharebest\Webtrees\Individual; |
27
|
|
|
use Fisharebest\Webtrees\Media; |
28
|
|
|
use Fisharebest\Webtrees\Note; |
29
|
|
|
use Fisharebest\Webtrees\Repository; |
30
|
|
|
use Fisharebest\Webtrees\Services\DataFixService; |
31
|
|
|
use Fisharebest\Webtrees\Source; |
32
|
|
|
use Fisharebest\Webtrees\Submitter; |
33
|
|
|
use Fisharebest\Webtrees\Tree; |
34
|
|
|
use Illuminate\Database\Capsule\Manager as DB; |
35
|
|
|
use Illuminate\Database\Query\Builder; |
36
|
|
|
use Illuminate\Support\Collection; |
37
|
|
|
use Throwable; |
38
|
|
|
|
39
|
|
|
use function addcslashes; |
40
|
|
|
use function asort; |
41
|
|
|
use function preg_match; |
42
|
|
|
use function preg_quote; |
43
|
|
|
use function preg_replace; |
44
|
|
|
use function view; |
45
|
|
|
|
46
|
|
|
/** |
47
|
|
|
* Class FixSearchAndReplace |
48
|
|
|
*/ |
49
|
|
|
class FixSearchAndReplace extends AbstractModule implements ModuleDataFixInterface |
50
|
|
|
{ |
51
|
|
|
use ModuleDataFixTrait; |
|
|
|
|
52
|
|
|
|
53
|
|
|
// A regular expression that never matches. |
54
|
|
|
private const INVALID_REGEX = '/(?!)/'; |
55
|
|
|
|
56
|
|
|
/** @var DataFixService */ |
57
|
|
|
private $data_fix_service; |
58
|
|
|
|
59
|
|
|
/** |
60
|
|
|
* FixMissingDeaths constructor. |
61
|
|
|
* |
62
|
|
|
* @param DataFixService $data_fix_service |
63
|
|
|
*/ |
64
|
|
|
public function __construct(DataFixService $data_fix_service) |
65
|
|
|
{ |
66
|
|
|
$this->data_fix_service = $data_fix_service; |
67
|
|
|
} |
68
|
|
|
|
69
|
|
|
/** |
70
|
|
|
* How should this module be identified in the control panel, etc.? |
71
|
|
|
* |
72
|
|
|
* @return string |
73
|
|
|
*/ |
74
|
|
|
public function title(): string |
75
|
|
|
{ |
76
|
|
|
/* I18N: Name of a module */ |
77
|
|
|
return I18N::translate('Search and replace'); |
78
|
|
|
} |
79
|
|
|
|
80
|
|
|
/** |
81
|
|
|
* A sentence describing what this module does. |
82
|
|
|
* |
83
|
|
|
* @return string |
84
|
|
|
*/ |
85
|
|
|
public function description(): string |
86
|
|
|
{ |
87
|
|
|
/* I18N: Description of a “Data fix” module */ |
88
|
|
|
return I18N::translate('Search and replace text, using simple searches or advanced pattern matching.'); |
89
|
|
|
} |
90
|
|
|
|
91
|
|
|
/** |
92
|
|
|
* Options form. |
93
|
|
|
* |
94
|
|
|
* @param Tree $tree |
95
|
|
|
* |
96
|
|
|
* @return string |
97
|
|
|
*/ |
98
|
|
|
public function fixOptions(Tree $tree): string |
99
|
|
|
{ |
100
|
|
|
$methods = [ |
101
|
|
|
'exact' => I18N::translate('Match the exact text, even if it occurs in the middle of a word.'), |
102
|
|
|
'words' => I18N::translate('Match the exact text, unless it occurs in the middle of a word.'), |
103
|
|
|
'wildcards' => I18N::translate('Use a “?” to match a single character, use “*” to match zero or more characters.'), |
104
|
|
|
/* I18N: http://en.wikipedia.org/wiki/Regular_expression */ |
105
|
|
|
'regex' => I18N::translate('Regular expressions are an advanced pattern matching technique.') . '<br>' . I18N::translate('See %s for more information.', '<a href="http://php.net/manual/regexp.reference.php">php.net/manual/regexp.reference.php</a>'), |
106
|
|
|
]; |
107
|
|
|
|
108
|
|
|
$types = [ |
109
|
|
|
Family::RECORD_TYPE => I18N::translate('Families'), |
110
|
|
|
Individual::RECORD_TYPE => I18N::translate('Individuals'), |
111
|
|
|
Media::RECORD_TYPE => I18N::translate('Media objects'), |
112
|
|
|
Note::RECORD_TYPE => I18N::translate('Notes'), |
113
|
|
|
Repository::RECORD_TYPE => I18N::translate('Repositories'), |
114
|
|
|
Source::RECORD_TYPE => I18N::translate('Sources'), |
115
|
|
|
Submitter::RECORD_TYPE => I18N::translate('Submitters'), |
116
|
|
|
]; |
117
|
|
|
|
118
|
|
|
asort($types); |
119
|
|
|
|
120
|
|
|
return view('modules/fix-search-and-replace/options', [ |
121
|
|
|
'default_method' => 'exact', |
122
|
|
|
'default_type' => Individual::RECORD_TYPE, |
123
|
|
|
'methods' => $methods, |
124
|
|
|
'types' => $types, |
125
|
|
|
]); |
126
|
|
|
} |
127
|
|
|
|
128
|
|
|
/** |
129
|
|
|
* A list of all records that need examining. This may include records |
130
|
|
|
* that do not need updating, if we can't detect this quickly using SQL. |
131
|
|
|
* |
132
|
|
|
* @param Tree $tree |
133
|
|
|
* @param array<string,string> $params |
134
|
|
|
* |
135
|
|
|
* @return Collection<string>|null |
136
|
|
|
*/ |
137
|
|
|
protected function familiesToFix(Tree $tree, array $params): ?Collection |
138
|
|
|
{ |
139
|
|
|
if ($params['type'] !== Family::RECORD_TYPE || $params['search'] === '') { |
140
|
|
|
return null; |
141
|
|
|
} |
142
|
|
|
|
143
|
|
|
$query = DB::table('families')->where('f_file', '=', $tree->id()); |
144
|
|
|
$this->recordQuery($query, 'f_gedcom', $params); |
145
|
|
|
|
146
|
|
|
return $query->pluck('f_id'); |
147
|
|
|
} |
148
|
|
|
|
149
|
|
|
/** |
150
|
|
|
* A list of all records that need examining. This may include records |
151
|
|
|
* that do not need updating, if we can't detect this quickly using SQL. |
152
|
|
|
* |
153
|
|
|
* @param Tree $tree |
154
|
|
|
* @param array<string,string> $params |
155
|
|
|
* |
156
|
|
|
* @return Collection<string>|null |
157
|
|
|
*/ |
158
|
|
|
protected function individualsToFix(Tree $tree, array $params): ?Collection |
159
|
|
|
{ |
160
|
|
|
if ($params['type'] !== Individual::RECORD_TYPE || $params['search'] === '') { |
161
|
|
|
return null; |
162
|
|
|
} |
163
|
|
|
|
164
|
|
|
$query = DB::table('individuals') |
165
|
|
|
->where('i_file', '=', $tree->id()); |
166
|
|
|
|
167
|
|
|
$this->recordQuery($query, 'i_gedcom', $params); |
168
|
|
|
|
169
|
|
|
return $query->pluck('i_id'); |
170
|
|
|
} |
171
|
|
|
|
172
|
|
|
/** |
173
|
|
|
* A list of all records that need examining. This may include records |
174
|
|
|
* that do not need updating, if we can't detect this quickly using SQL. |
175
|
|
|
* |
176
|
|
|
* @param Tree $tree |
177
|
|
|
* @param array<string,string> $params |
178
|
|
|
* |
179
|
|
|
* @return Collection<string>|null |
180
|
|
|
*/ |
181
|
|
|
protected function mediaToFix(Tree $tree, array $params): ?Collection |
182
|
|
|
{ |
183
|
|
|
if ($params['type'] !== Media::RECORD_TYPE || $params['search'] === '') { |
184
|
|
|
return null; |
185
|
|
|
} |
186
|
|
|
|
187
|
|
|
$query = DB::table('media') |
188
|
|
|
->where('m_file', '=', $tree->id()); |
189
|
|
|
|
190
|
|
|
$this->recordQuery($query, 'm_gedcom', $params); |
191
|
|
|
|
192
|
|
|
return $query->pluck('m_id'); |
193
|
|
|
} |
194
|
|
|
|
195
|
|
|
/** |
196
|
|
|
* A list of all records that need examining. This may include records |
197
|
|
|
* that do not need updating, if we can't detect this quickly using SQL. |
198
|
|
|
* |
199
|
|
|
* @param Tree $tree |
200
|
|
|
* @param array<string,string> $params |
201
|
|
|
* |
202
|
|
|
* @return Collection<string>|null |
203
|
|
|
*/ |
204
|
|
|
protected function notesToFix(Tree $tree, array $params): ?Collection |
205
|
|
|
{ |
206
|
|
|
if ($params['type'] !== Note::RECORD_TYPE || $params['search'] === '') { |
207
|
|
|
return null; |
208
|
|
|
} |
209
|
|
|
|
210
|
|
|
$query = DB::table('other') |
211
|
|
|
->where('o_file', '=', $tree->id()) |
212
|
|
|
->where('o_type', '=', Note::RECORD_TYPE); |
213
|
|
|
|
214
|
|
|
$this->recordQuery($query, 'o_gedcom', $params); |
215
|
|
|
|
216
|
|
|
return $query->pluck('o_id'); |
217
|
|
|
} |
218
|
|
|
|
219
|
|
|
/** |
220
|
|
|
* A list of all records that need examining. This may include records |
221
|
|
|
* that do not need updating, if we can't detect this quickly using SQL. |
222
|
|
|
* |
223
|
|
|
* @param Tree $tree |
224
|
|
|
* @param array<string,string> $params |
225
|
|
|
* |
226
|
|
|
* @return Collection<string>|null |
227
|
|
|
*/ |
228
|
|
|
protected function repositoriesToFix(Tree $tree, array $params): ?Collection |
229
|
|
|
{ |
230
|
|
|
if ($params['type'] !== Repository::RECORD_TYPE || $params['search'] === '') { |
231
|
|
|
return null; |
232
|
|
|
} |
233
|
|
|
|
234
|
|
|
$query = DB::table('other') |
235
|
|
|
->where('o_file', '=', $tree->id()) |
236
|
|
|
->where('o_type', '=', Repository::RECORD_TYPE); |
237
|
|
|
|
238
|
|
|
$this->recordQuery($query, 'o_gedcom', $params); |
239
|
|
|
|
240
|
|
|
return $query->pluck('o_id'); |
241
|
|
|
} |
242
|
|
|
|
243
|
|
|
/** |
244
|
|
|
* A list of all records that need examining. This may include records |
245
|
|
|
* that do not need updating, if we can't detect this quickly using SQL. |
246
|
|
|
* |
247
|
|
|
* @param Tree $tree |
248
|
|
|
* @param array<string,string> $params |
249
|
|
|
* |
250
|
|
|
* @return Collection<string>|null |
251
|
|
|
*/ |
252
|
|
|
protected function sourcesToFix(Tree $tree, array $params): ?Collection |
253
|
|
|
{ |
254
|
|
|
if ($params['type'] !== Source::RECORD_TYPE || $params['search'] === '') { |
255
|
|
|
return null; |
256
|
|
|
} |
257
|
|
|
|
258
|
|
|
$query = DB::table('sources') |
259
|
|
|
->where('s_file', '=', $tree->id()); |
260
|
|
|
|
261
|
|
|
$this->recordQuery($query, 's_gedcom', $params); |
262
|
|
|
|
263
|
|
|
return $query->pluck('s_id'); |
264
|
|
|
} |
265
|
|
|
|
266
|
|
|
/** |
267
|
|
|
* A list of all records that need examining. This may include records |
268
|
|
|
* that do not need updating, if we can't detect this quickly using SQL. |
269
|
|
|
* |
270
|
|
|
* @param Tree $tree |
271
|
|
|
* @param array<string,string> $params |
272
|
|
|
* |
273
|
|
|
* @return Collection<string>|null |
274
|
|
|
*/ |
275
|
|
|
protected function submittersToFix(Tree $tree, array $params): ?Collection |
276
|
|
|
{ |
277
|
|
|
if ($params['type'] !== Submitter::RECORD_TYPE || $params['search'] === '') { |
278
|
|
|
return null; |
279
|
|
|
} |
280
|
|
|
|
281
|
|
|
$query = DB::table('other') |
282
|
|
|
->where('o_file', '=', $tree->id()) |
283
|
|
|
->where('o_type', '=', Submitter::RECORD_TYPE); |
284
|
|
|
|
285
|
|
|
$this->recordQuery($query, 'o_gedcom', $params); |
286
|
|
|
|
287
|
|
|
return $query->pluck('o_id'); |
288
|
|
|
} |
289
|
|
|
|
290
|
|
|
/** |
291
|
|
|
* Does a record need updating? |
292
|
|
|
* |
293
|
|
|
* @param GedcomRecord $record |
294
|
|
|
* @param array<string,string> $params |
295
|
|
|
* |
296
|
|
|
* @return bool |
297
|
|
|
*/ |
298
|
|
|
public function doesRecordNeedUpdate(GedcomRecord $record, array $params): bool |
299
|
|
|
{ |
300
|
|
|
return preg_match($this->createRegex($params), $record->gedcom()) === 1; |
301
|
|
|
} |
302
|
|
|
|
303
|
|
|
/** |
304
|
|
|
* Show the changes we would make |
305
|
|
|
* |
306
|
|
|
* @param GedcomRecord $record |
307
|
|
|
* @param array<string,string> $params |
308
|
|
|
* |
309
|
|
|
* @return string |
310
|
|
|
*/ |
311
|
|
|
public function previewUpdate(GedcomRecord $record, array $params): string |
312
|
|
|
{ |
313
|
|
|
$old = $record->gedcom(); |
314
|
|
|
$new = $this->updateGedcom($record, $params); |
315
|
|
|
|
316
|
|
|
return $this->data_fix_service->gedcomDiff($record->tree(), $old, $new); |
317
|
|
|
} |
318
|
|
|
|
319
|
|
|
/** |
320
|
|
|
* Fix a record |
321
|
|
|
* |
322
|
|
|
* @param GedcomRecord $record |
323
|
|
|
* @param array<string,string> $params |
324
|
|
|
* |
325
|
|
|
* @return void |
326
|
|
|
*/ |
327
|
|
|
public function updateRecord(GedcomRecord $record, array $params): void |
328
|
|
|
{ |
329
|
|
|
$record->updateRecord($this->updateGedcom($record, $params), false); |
330
|
|
|
} |
331
|
|
|
|
332
|
|
|
/** |
333
|
|
|
* @param GedcomRecord $record |
334
|
|
|
* @param array<string,string> $params |
335
|
|
|
* |
336
|
|
|
* @return string |
337
|
|
|
*/ |
338
|
|
|
private function updateGedcom(GedcomRecord $record, array $params): string |
339
|
|
|
{ |
340
|
|
|
// Allow "\n" to indicate a line-feed in replacement text. |
341
|
|
|
// Back-references such as $1, $2 are handled automatically. |
342
|
|
|
$replace = strtr($params['replace'], ['\\n', "\n"]); |
343
|
|
|
|
344
|
|
|
$regex = $this->createRegex($params); |
345
|
|
|
|
346
|
|
|
return preg_replace($regex, $replace, $record->gedcom()); |
347
|
|
|
} |
348
|
|
|
|
349
|
|
|
/** |
350
|
|
|
* Create a regular expression from the search pattern. |
351
|
|
|
* |
352
|
|
|
* @param array<string,string> $params |
353
|
|
|
* |
354
|
|
|
* @return string |
355
|
|
|
*/ |
356
|
|
|
private function createRegex(array $params): string |
357
|
|
|
{ |
358
|
|
|
$search = $params['search']; |
359
|
|
|
$method = $params['method']; |
360
|
|
|
$case = $params['case']; |
361
|
|
|
|
362
|
|
|
switch ($method) { |
363
|
|
|
case 'exact': |
364
|
|
|
return '/' . preg_quote($search, '/') . '/' . $case; |
365
|
|
|
|
366
|
|
|
case 'words': |
367
|
|
|
return '/\b' . preg_quote($search, '/') . '\b/' . $case; |
368
|
|
|
|
369
|
|
|
case 'wildcards': |
370
|
|
|
return '/\b' . strtr(preg_quote($search, '/'), ['\*' => '.*', '\?' => '.']) . '\b/' . $case; |
371
|
|
|
|
372
|
|
|
case 'regex': |
373
|
|
|
$regex = '/' . addcslashes($search, '/') . '/' . $case; |
374
|
|
|
|
375
|
|
|
try { |
376
|
|
|
// A valid regex on an empty string returns zero. |
377
|
|
|
// An invalid regex on an empty string returns false and throws a warning. |
378
|
|
|
preg_match($regex, ''); |
379
|
|
|
} catch (Throwable $ex) { |
380
|
|
|
$regex = self::INVALID_REGEX; |
381
|
|
|
} |
382
|
|
|
|
383
|
|
|
return $regex; |
384
|
|
|
} |
385
|
|
|
|
386
|
|
|
throw new HttpNotFoundException(); |
387
|
|
|
} |
388
|
|
|
|
389
|
|
|
/** |
390
|
|
|
* Create a regular expression from the search pattern. |
391
|
|
|
* |
392
|
|
|
* @param Builder $query |
393
|
|
|
* @param string $column |
394
|
|
|
* @param array<string,string> $params |
395
|
|
|
* |
396
|
|
|
* @return void |
397
|
|
|
*/ |
398
|
|
|
private function recordQuery(Builder $query, string $column, array $params): void |
399
|
|
|
{ |
400
|
|
|
$search = $params['search']; |
401
|
|
|
$method = $params['method']; |
402
|
|
|
$like = addcslashes($search, '_%\\'); |
403
|
|
|
|
404
|
|
|
switch ($method) { |
405
|
|
|
case 'exact': |
406
|
|
|
case 'words': |
407
|
|
|
$query->where($column, 'LIKE', '%' . $like . '$'); |
408
|
|
|
break; |
409
|
|
|
|
410
|
|
|
case 'wildcards': |
411
|
|
|
$like = strtr($like, ['?' => '_', '*' => '%']); |
412
|
|
|
$query->where($column, 'LIKE', '%' . $like . '$'); |
413
|
|
|
break; |
414
|
|
|
|
415
|
|
|
case 'regex': |
416
|
|
|
switch (DB::connection()->getDriverName()) { |
417
|
|
|
case 'sqlite': |
418
|
|
|
case 'mysql': |
419
|
|
|
$query->where($column, 'REGEXP', $search); |
420
|
|
|
break; |
421
|
|
|
|
422
|
|
|
case 'pgsql': |
423
|
|
|
$query->where($column, '~', $search); |
424
|
|
|
break; |
425
|
|
|
|
426
|
|
|
case 'sqlsvr': |
427
|
|
|
// Not available |
428
|
|
|
break; |
429
|
|
|
} |
430
|
|
|
break; |
431
|
|
|
} |
432
|
|
|
} |
433
|
|
|
} |
434
|
|
|
|