fisharebest /
webtrees
| Total Complexity | 244 |
| Total Lines | 1130 |
| Duplicated Lines | 0 % |
| Changes | 0 | ||
Complex classes like FunctionsImport often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use FunctionsImport, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 43 | class FunctionsImport |
||
| 44 | { |
||
| 45 | /** |
||
| 46 | * Tidy up a gedcom record on import, so that we can access it consistently/efficiently. |
||
| 47 | * |
||
| 48 | * @param string $rec |
||
| 49 | * @param Tree $tree |
||
| 50 | * |
||
| 51 | * @return string |
||
| 52 | */ |
||
| 53 | public static function reformatRecord($rec, Tree $tree): string |
||
| 54 | { |
||
| 55 | // Strip out mac/msdos line endings |
||
| 56 | $rec = preg_replace("/[\r\n]+/", "\n", $rec); |
||
| 57 | |||
| 58 | // Extract lines from the record; lines consist of: level + optional xref + tag + optional data |
||
| 59 | $num_matches = preg_match_all('/^[ \t]*(\d+)[ \t]*(@[^@]*@)?[ \t]*(\w+)[ \t]?(.*)$/m', $rec, $matches, PREG_SET_ORDER); |
||
| 60 | |||
| 61 | // Process the record line-by-line |
||
| 62 | $newrec = ''; |
||
| 63 | foreach ($matches as $n => $match) { |
||
| 64 | [, $level, $xref, $tag, $data] = $match; |
||
| 65 | $tag = strtoupper($tag); // Tags should always be upper case |
||
| 66 | switch ($tag) { |
||
| 67 | // Convert PhpGedView tags to WT |
||
| 68 | case '_PGVU': |
||
| 69 | $tag = '_WT_USER'; |
||
| 70 | break; |
||
| 71 | case '_PGV_OBJS': |
||
| 72 | $tag = '_WT_OBJE_SORT'; |
||
| 73 | break; |
||
| 74 | // Convert FTM-style "TAG_FORMAL_NAME" into "TAG". |
||
| 75 | case 'ABBREVIATION': |
||
| 76 | $tag = 'ABBR'; |
||
| 77 | break; |
||
| 78 | case 'ADDRESS': |
||
| 79 | $tag = 'ADDR'; |
||
| 80 | break; |
||
| 81 | case 'ADDRESS1': |
||
| 82 | $tag = 'ADR1'; |
||
| 83 | break; |
||
| 84 | case 'ADDRESS2': |
||
| 85 | $tag = 'ADR2'; |
||
| 86 | break; |
||
| 87 | case 'ADDRESS3': |
||
| 88 | $tag = 'ADR3'; |
||
| 89 | break; |
||
| 90 | case 'ADOPTION': |
||
| 91 | $tag = 'ADOP'; |
||
| 92 | break; |
||
| 93 | case 'ADULT_CHRISTENING': |
||
| 94 | $tag = 'CHRA'; |
||
| 95 | break; |
||
| 96 | case 'AFN': |
||
| 97 | // AFN values are upper case |
||
| 98 | $data = strtoupper($data); |
||
| 99 | break; |
||
| 100 | case 'AGENCY': |
||
| 101 | $tag = 'AGNC'; |
||
| 102 | break; |
||
| 103 | case 'ALIAS': |
||
| 104 | $tag = 'ALIA'; |
||
| 105 | break; |
||
| 106 | case 'ANCESTORS': |
||
| 107 | $tag = 'ANCE'; |
||
| 108 | break; |
||
| 109 | case 'ANCES_INTEREST': |
||
| 110 | $tag = 'ANCI'; |
||
| 111 | break; |
||
| 112 | case 'ANNULMENT': |
||
| 113 | $tag = 'ANUL'; |
||
| 114 | break; |
||
| 115 | case 'ASSOCIATES': |
||
| 116 | $tag = 'ASSO'; |
||
| 117 | break; |
||
| 118 | case 'AUTHOR': |
||
| 119 | $tag = 'AUTH'; |
||
| 120 | break; |
||
| 121 | case 'BAPTISM': |
||
| 122 | $tag = 'BAPM'; |
||
| 123 | break; |
||
| 124 | case 'BAPTISM_LDS': |
||
| 125 | $tag = 'BAPL'; |
||
| 126 | break; |
||
| 127 | case 'BAR_MITZVAH': |
||
| 128 | $tag = 'BARM'; |
||
| 129 | break; |
||
| 130 | case 'BAS_MITZVAH': |
||
| 131 | $tag = 'BASM'; |
||
| 132 | break; |
||
| 133 | case 'BIRTH': |
||
| 134 | $tag = 'BIRT'; |
||
| 135 | break; |
||
| 136 | case 'BLESSING': |
||
| 137 | $tag = 'BLES'; |
||
| 138 | break; |
||
| 139 | case 'BURIAL': |
||
| 140 | $tag = 'BURI'; |
||
| 141 | break; |
||
| 142 | case 'CALL_NUMBER': |
||
| 143 | $tag = 'CALN'; |
||
| 144 | break; |
||
| 145 | case 'CASTE': |
||
| 146 | $tag = 'CAST'; |
||
| 147 | break; |
||
| 148 | case 'CAUSE': |
||
| 149 | $tag = 'CAUS'; |
||
| 150 | break; |
||
| 151 | case 'CENSUS': |
||
| 152 | $tag = 'CENS'; |
||
| 153 | break; |
||
| 154 | case 'CHANGE': |
||
| 155 | $tag = 'CHAN'; |
||
| 156 | break; |
||
| 157 | case 'CHARACTER': |
||
| 158 | $tag = 'CHAR'; |
||
| 159 | break; |
||
| 160 | case 'CHILD': |
||
| 161 | $tag = 'CHIL'; |
||
| 162 | break; |
||
| 163 | case 'CHILDREN_COUNT': |
||
| 164 | $tag = 'NCHI'; |
||
| 165 | break; |
||
| 166 | case 'CHRISTENING': |
||
| 167 | $tag = 'CHR'; |
||
| 168 | break; |
||
| 169 | case 'CONCATENATION': |
||
| 170 | $tag = 'CONC'; |
||
| 171 | break; |
||
| 172 | case 'CONFIRMATION': |
||
| 173 | $tag = 'CONF'; |
||
| 174 | break; |
||
| 175 | case 'CONFIRMATION_LDS': |
||
| 176 | $tag = 'CONL'; |
||
| 177 | break; |
||
| 178 | case 'CONTINUED': |
||
| 179 | $tag = 'CONT'; |
||
| 180 | break; |
||
| 181 | case 'COPYRIGHT': |
||
| 182 | $tag = 'COPR'; |
||
| 183 | break; |
||
| 184 | case 'CORPORATE': |
||
| 185 | $tag = 'CORP'; |
||
| 186 | break; |
||
| 187 | case 'COUNTRY': |
||
| 188 | $tag = 'CTRY'; |
||
| 189 | break; |
||
| 190 | case 'CREMATION': |
||
| 191 | $tag = 'CREM'; |
||
| 192 | break; |
||
| 193 | case 'DATE': |
||
| 194 | // Preserve text from INT dates |
||
| 195 | if (strpos($data, '(') !== false) { |
||
| 196 | [$date, $text] = explode('(', $data, 2); |
||
| 197 | $text = ' (' . $text; |
||
| 198 | } else { |
||
| 199 | $date = $data; |
||
| 200 | $text = ''; |
||
| 201 | } |
||
| 202 | // Capitals |
||
| 203 | $date = strtoupper($date); |
||
| 204 | // Temporarily add leading/trailing spaces, to allow efficient matching below |
||
| 205 | $date = " {$date} "; |
||
| 206 | // Ensure space digits and letters |
||
| 207 | $date = preg_replace('/([A-Z])(\d)/', '$1 $2', $date); |
||
| 208 | $date = preg_replace('/(\d)([A-Z])/', '$1 $2', $date); |
||
| 209 | // Ensure space before/after calendar escapes |
||
| 210 | $date = preg_replace('/@#[^@]+@/', ' $0 ', $date); |
||
| 211 | // "BET." => "BET" |
||
| 212 | $date = preg_replace('/(\w\w)\./', '$1', $date); |
||
| 213 | // "CIR" => "ABT" |
||
| 214 | $date = str_replace(' CIR ', ' ABT ', $date); |
||
| 215 | $date = str_replace(' APX ', ' ABT ', $date); |
||
| 216 | // B.C. => BC (temporarily, to allow easier handling of ".") |
||
| 217 | $date = str_replace(' B.C. ', ' BC ', $date); |
||
| 218 | // TMG uses "EITHER X OR Y" |
||
| 219 | $date = preg_replace('/^ EITHER (.+) OR (.+)/', ' BET $1 AND $2', $date); |
||
| 220 | // "BET X - Y " => "BET X AND Y" |
||
| 221 | $date = preg_replace('/^(.* BET .+) - (.+)/', '$1 AND $2', $date); |
||
| 222 | $date = preg_replace('/^(.* FROM .+) - (.+)/', '$1 TO $2', $date); |
||
| 223 | // "@#ESC@ FROM X TO Y" => "FROM @#ESC@ X TO @#ESC@ Y" |
||
| 224 | $date = preg_replace('/^ +(@#[^@]+@) +FROM +(.+) +TO +(.+)/', ' FROM $1 $2 TO $1 $3', $date); |
||
| 225 | $date = preg_replace('/^ +(@#[^@]+@) +BET +(.+) +AND +(.+)/', ' BET $1 $2 AND $1 $3', $date); |
||
| 226 | // "@#ESC@ AFT X" => "AFT @#ESC@ X" |
||
| 227 | $date = preg_replace('/^ +(@#[^@]+@) +(FROM|BET|TO|AND|BEF|AFT|CAL|EST|INT|ABT) +(.+)/', ' $2 $1 $3', $date); |
||
| 228 | // Ignore any remaining punctuation, e.g. "14-MAY, 1900" => "14 MAY 1900" |
||
| 229 | // (don't change "/" - it is used in NS/OS dates) |
||
| 230 | $date = preg_replace('/[.,:;-]/', ' ', $date); |
||
| 231 | // BC => B.C. |
||
| 232 | $date = str_replace(' BC ', ' B.C. ', $date); |
||
| 233 | // Append the "INT" text |
||
| 234 | $data = $date . $text; |
||
| 235 | break; |
||
| 236 | case 'DEATH': |
||
| 237 | $tag = 'DEAT'; |
||
| 238 | break; |
||
| 239 | case '_DEATH_OF_SPOUSE': |
||
| 240 | $tag = '_DETS'; |
||
| 241 | break; |
||
| 242 | case '_DEGREE': |
||
| 243 | $tag = '_DEG'; |
||
| 244 | break; |
||
| 245 | case 'DESCENDANTS': |
||
| 246 | $tag = 'DESC'; |
||
| 247 | break; |
||
| 248 | case 'DESCENDANT_INT': |
||
| 249 | $tag = 'DESI'; |
||
| 250 | break; |
||
| 251 | case 'DESTINATION': |
||
| 252 | $tag = 'DEST'; |
||
| 253 | break; |
||
| 254 | case 'DIVORCE': |
||
| 255 | $tag = 'DIV'; |
||
| 256 | break; |
||
| 257 | case 'DIVORCE_FILED': |
||
| 258 | $tag = 'DIVF'; |
||
| 259 | break; |
||
| 260 | case 'EDUCATION': |
||
| 261 | $tag = 'EDUC'; |
||
| 262 | break; |
||
| 263 | case 'EMIGRATION': |
||
| 264 | $tag = 'EMIG'; |
||
| 265 | break; |
||
| 266 | case 'ENDOWMENT': |
||
| 267 | $tag = 'ENDL'; |
||
| 268 | break; |
||
| 269 | case 'ENGAGEMENT': |
||
| 270 | $tag = 'ENGA'; |
||
| 271 | break; |
||
| 272 | case 'EVENT': |
||
| 273 | $tag = 'EVEN'; |
||
| 274 | break; |
||
| 275 | case 'FACSIMILE': |
||
| 276 | $tag = 'FAX'; |
||
| 277 | break; |
||
| 278 | case 'FAMILY': |
||
| 279 | $tag = 'FAM'; |
||
| 280 | break; |
||
| 281 | case 'FAMILY_CHILD': |
||
| 282 | $tag = 'FAMC'; |
||
| 283 | break; |
||
| 284 | case 'FAMILY_FILE': |
||
| 285 | $tag = 'FAMF'; |
||
| 286 | break; |
||
| 287 | case 'FAMILY_SPOUSE': |
||
| 288 | $tag = 'FAMS'; |
||
| 289 | break; |
||
| 290 | case 'FIRST_COMMUNION': |
||
| 291 | $tag = 'FCOM'; |
||
| 292 | break; |
||
| 293 | case '_FILE': |
||
| 294 | $tag = 'FILE'; |
||
| 295 | break; |
||
| 296 | case 'FORMAT': |
||
| 297 | case 'FORM': |
||
| 298 | $tag = 'FORM'; |
||
| 299 | // Consistent commas |
||
| 300 | $data = preg_replace('/ *, */', ', ', $data); |
||
| 301 | break; |
||
| 302 | case 'GEDCOM': |
||
| 303 | $tag = 'GEDC'; |
||
| 304 | break; |
||
| 305 | case 'GIVEN_NAME': |
||
| 306 | $tag = 'GIVN'; |
||
| 307 | break; |
||
| 308 | case 'GRADUATION': |
||
| 309 | $tag = 'GRAD'; |
||
| 310 | break; |
||
| 311 | case 'HEADER': |
||
| 312 | case 'HEAD': |
||
| 313 | $tag = 'HEAD'; |
||
| 314 | // HEAD records don't have an XREF or DATA |
||
| 315 | if ($level === '0') { |
||
| 316 | $xref = ''; |
||
| 317 | $data = ''; |
||
| 318 | } |
||
| 319 | break; |
||
| 320 | case 'HUSBAND': |
||
| 321 | $tag = 'HUSB'; |
||
| 322 | break; |
||
| 323 | case 'IDENT_NUMBER': |
||
| 324 | $tag = 'IDNO'; |
||
| 325 | break; |
||
| 326 | case 'IMMIGRATION': |
||
| 327 | $tag = 'IMMI'; |
||
| 328 | break; |
||
| 329 | case 'INDIVIDUAL': |
||
| 330 | $tag = 'INDI'; |
||
| 331 | break; |
||
| 332 | case 'LANGUAGE': |
||
| 333 | $tag = 'LANG'; |
||
| 334 | break; |
||
| 335 | case 'LATITUDE': |
||
| 336 | $tag = 'LATI'; |
||
| 337 | break; |
||
| 338 | case 'LONGITUDE': |
||
| 339 | $tag = 'LONG'; |
||
| 340 | break; |
||
| 341 | case 'MARRIAGE': |
||
| 342 | $tag = 'MARR'; |
||
| 343 | break; |
||
| 344 | case 'MARRIAGE_BANN': |
||
| 345 | $tag = 'MARB'; |
||
| 346 | break; |
||
| 347 | case 'MARRIAGE_COUNT': |
||
| 348 | $tag = 'NMR'; |
||
| 349 | break; |
||
| 350 | case 'MARRIAGE_CONTRACT': |
||
| 351 | $tag = 'MARC'; |
||
| 352 | break; |
||
| 353 | case 'MARRIAGE_LICENSE': |
||
| 354 | $tag = 'MARL'; |
||
| 355 | break; |
||
| 356 | case 'MARRIAGE_SETTLEMENT': |
||
| 357 | $tag = 'MARS'; |
||
| 358 | break; |
||
| 359 | case 'MEDIA': |
||
| 360 | $tag = 'MEDI'; |
||
| 361 | break; |
||
| 362 | case '_MEDICAL': |
||
| 363 | $tag = '_MDCL'; |
||
| 364 | break; |
||
| 365 | case '_MILITARY_SERVICE': |
||
| 366 | $tag = '_MILT'; |
||
| 367 | break; |
||
| 368 | case 'NAME': |
||
| 369 | // Tidy up whitespace |
||
| 370 | $data = preg_replace('/ +/', ' ', trim($data)); |
||
| 371 | break; |
||
| 372 | case 'NAME_PREFIX': |
||
| 373 | $tag = 'NPFX'; |
||
| 374 | break; |
||
| 375 | case 'NAME_SUFFIX': |
||
| 376 | $tag = 'NSFX'; |
||
| 377 | break; |
||
| 378 | case 'NATIONALITY': |
||
| 379 | $tag = 'NATI'; |
||
| 380 | break; |
||
| 381 | case 'NATURALIZATION': |
||
| 382 | $tag = 'NATU'; |
||
| 383 | break; |
||
| 384 | case 'NICKNAME': |
||
| 385 | $tag = 'NICK'; |
||
| 386 | break; |
||
| 387 | case 'OBJECT': |
||
| 388 | $tag = 'OBJE'; |
||
| 389 | break; |
||
| 390 | case 'OCCUPATION': |
||
| 391 | $tag = 'OCCU'; |
||
| 392 | break; |
||
| 393 | case 'ORDINANCE': |
||
| 394 | $tag = 'ORDI'; |
||
| 395 | break; |
||
| 396 | case 'ORDINATION': |
||
| 397 | $tag = 'ORDN'; |
||
| 398 | break; |
||
| 399 | case 'PEDIGREE': |
||
| 400 | case 'PEDI': |
||
| 401 | $tag = 'PEDI'; |
||
| 402 | // PEDI values are lower case |
||
| 403 | $data = strtolower($data); |
||
| 404 | break; |
||
| 405 | case 'PHONE': |
||
| 406 | $tag = 'PHON'; |
||
| 407 | break; |
||
| 408 | case 'PHONETIC': |
||
| 409 | $tag = 'FONE'; |
||
| 410 | break; |
||
| 411 | case 'PHY_DESCRIPTION': |
||
| 412 | $tag = 'DSCR'; |
||
| 413 | break; |
||
| 414 | case 'PLACE': |
||
| 415 | case 'PLAC': |
||
| 416 | $tag = 'PLAC'; |
||
| 417 | // Consistent commas |
||
| 418 | $data = preg_replace('/ *, */', ', ', $data); |
||
| 419 | // The Master Genealogist stores LAT/LONG data in the PLAC field, e.g. Pennsylvania, USA, 395945N0751013W |
||
| 420 | if (preg_match('/(.*), (\d\d)(\d\d)(\d\d)([NS])(\d\d\d)(\d\d)(\d\d)([EW])$/', $data, $match)) { |
||
| 421 | $data = |
||
| 422 | $match[1] . "\n" . |
||
| 423 | ($level + 1) . " MAP\n" . |
||
| 424 | ($level + 2) . ' LATI ' . ($match[5] . round($match[2] + ($match[3] / 60) + ($match[4] / 3600), 4)) . "\n" . |
||
| 425 | ($level + 2) . ' LONG ' . ($match[9] . round($match[6] + ($match[7] / 60) + ($match[8] / 3600), 4)); |
||
| 426 | } |
||
| 427 | break; |
||
| 428 | case 'POSTAL_CODE': |
||
| 429 | $tag = 'POST'; |
||
| 430 | break; |
||
| 431 | case 'PROBATE': |
||
| 432 | $tag = 'PROB'; |
||
| 433 | break; |
||
| 434 | case 'PROPERTY': |
||
| 435 | $tag = 'PROP'; |
||
| 436 | break; |
||
| 437 | case 'PUBLICATION': |
||
| 438 | $tag = 'PUBL'; |
||
| 439 | break; |
||
| 440 | case 'QUALITY_OF_DATA': |
||
| 441 | $tag = 'QUAL'; |
||
| 442 | break; |
||
| 443 | case 'REC_FILE_NUMBER': |
||
| 444 | $tag = 'RFN'; |
||
| 445 | break; |
||
| 446 | case 'REC_ID_NUMBER': |
||
| 447 | $tag = 'RIN'; |
||
| 448 | break; |
||
| 449 | case 'REFERENCE': |
||
| 450 | $tag = 'REFN'; |
||
| 451 | break; |
||
| 452 | case 'RELATIONSHIP': |
||
| 453 | $tag = 'RELA'; |
||
| 454 | break; |
||
| 455 | case 'RELIGION': |
||
| 456 | $tag = 'RELI'; |
||
| 457 | break; |
||
| 458 | case 'REPOSITORY': |
||
| 459 | $tag = 'REPO'; |
||
| 460 | break; |
||
| 461 | case 'RESIDENCE': |
||
| 462 | $tag = 'RESI'; |
||
| 463 | break; |
||
| 464 | case 'RESTRICTION': |
||
| 465 | case 'RESN': |
||
| 466 | $tag = 'RESN'; |
||
| 467 | // RESN values are lower case (confidential, privacy, locked, none) |
||
| 468 | $data = strtolower($data); |
||
| 469 | if ($data === 'invisible') { |
||
| 470 | $data = 'confidential'; // From old versions of Legacy. |
||
| 471 | } |
||
| 472 | break; |
||
| 473 | case 'RETIREMENT': |
||
| 474 | $tag = 'RETI'; |
||
| 475 | break; |
||
| 476 | case 'ROMANIZED': |
||
| 477 | $tag = 'ROMN'; |
||
| 478 | break; |
||
| 479 | case 'SEALING_CHILD': |
||
| 480 | $tag = 'SLGC'; |
||
| 481 | break; |
||
| 482 | case 'SEALING_SPOUSE': |
||
| 483 | $tag = 'SLGS'; |
||
| 484 | break; |
||
| 485 | case 'SOC_SEC_NUMBER': |
||
| 486 | $tag = 'SSN'; |
||
| 487 | break; |
||
| 488 | case 'SEX': |
||
| 489 | $data = strtoupper($data); |
||
| 490 | break; |
||
| 491 | case 'SOURCE': |
||
| 492 | $tag = 'SOUR'; |
||
| 493 | break; |
||
| 494 | case 'STATE': |
||
| 495 | $tag = 'STAE'; |
||
| 496 | break; |
||
| 497 | case 'STATUS': |
||
| 498 | case 'STAT': |
||
| 499 | $tag = 'STAT'; |
||
| 500 | if ($data === 'CANCELLED') { |
||
| 501 | // PhpGedView mis-spells this tag - correct it. |
||
| 502 | $data = 'CANCELED'; |
||
| 503 | } |
||
| 504 | break; |
||
| 505 | case 'SUBMISSION': |
||
| 506 | $tag = 'SUBN'; |
||
| 507 | break; |
||
| 508 | case 'SUBMITTER': |
||
| 509 | $tag = 'SUBM'; |
||
| 510 | break; |
||
| 511 | case 'SURNAME': |
||
| 512 | $tag = 'SURN'; |
||
| 513 | break; |
||
| 514 | case 'SURN_PREFIX': |
||
| 515 | $tag = 'SPFX'; |
||
| 516 | break; |
||
| 517 | case 'TEMPLE': |
||
| 518 | case 'TEMP': |
||
| 519 | $tag = 'TEMP'; |
||
| 520 | // Temple codes are upper case |
||
| 521 | $data = strtoupper($data); |
||
| 522 | break; |
||
| 523 | case 'TITLE': |
||
| 524 | $tag = 'TITL'; |
||
| 525 | break; |
||
| 526 | case 'TRAILER': |
||
| 527 | case 'TRLR': |
||
| 528 | $tag = 'TRLR'; |
||
| 529 | // TRLR records don't have an XREF or DATA |
||
| 530 | if ($level === '0') { |
||
| 531 | $xref = ''; |
||
| 532 | $data = ''; |
||
| 533 | } |
||
| 534 | break; |
||
| 535 | case 'VERSION': |
||
| 536 | $tag = 'VERS'; |
||
| 537 | break; |
||
| 538 | case 'WEB': |
||
| 539 | $tag = 'WWW'; |
||
| 540 | break; |
||
| 541 | } |
||
| 542 | // Suppress "Y", for facts/events with a DATE or PLAC |
||
| 543 | if ($data === 'y') { |
||
| 544 | $data = 'Y'; |
||
| 545 | } |
||
| 546 | if ($level === '1' && $data === 'Y') { |
||
| 547 | for ($i = $n + 1; $i < $num_matches - 1 && $matches[$i][1] !== '1'; ++$i) { |
||
| 548 | if ($matches[$i][3] === 'DATE' || $matches[$i][3] === 'PLAC') { |
||
| 549 | $data = ''; |
||
| 550 | break; |
||
| 551 | } |
||
| 552 | } |
||
| 553 | } |
||
| 554 | // Reassemble components back into a single line |
||
| 555 | switch ($tag) { |
||
| 556 | default: |
||
| 557 | // Remove tabs and multiple/leading/trailing spaces |
||
| 558 | if (strpos($data, "\t") !== false) { |
||
| 559 | $data = str_replace("\t", ' ', $data); |
||
| 560 | } |
||
| 561 | if (substr($data, 0, 1) === ' ' || substr($data, -1, 1) === ' ') { |
||
| 562 | $data = trim($data); |
||
| 563 | } |
||
| 564 | while (strpos($data, ' ')) { |
||
| 565 | $data = str_replace(' ', ' ', $data); |
||
| 566 | } |
||
| 567 | $newrec .= ($newrec ? "\n" : '') . $level . ' ' . ($level === '0' && $xref ? $xref . ' ' : '') . $tag . ($data === '' && $tag !== 'NOTE' ? '' : ' ' . $data); |
||
| 568 | break; |
||
| 569 | case 'NOTE': |
||
| 570 | case 'TEXT': |
||
| 571 | case 'DATA': |
||
| 572 | case 'CONT': |
||
| 573 | $newrec .= ($newrec ? "\n" : '') . $level . ' ' . ($level === '0' && $xref ? $xref . ' ' : '') . $tag . ($data === '' && $tag !== 'NOTE' ? '' : ' ' . $data); |
||
| 574 | break; |
||
| 575 | case 'FILE': |
||
| 576 | // Strip off the user-defined path prefix |
||
| 577 | $GEDCOM_MEDIA_PATH = $tree->getPreference('GEDCOM_MEDIA_PATH'); |
||
| 578 | if ($GEDCOM_MEDIA_PATH && strpos($data, $GEDCOM_MEDIA_PATH) === 0) { |
||
| 579 | $data = substr($data, strlen($GEDCOM_MEDIA_PATH)); |
||
| 580 | } |
||
| 581 | // convert backslashes in filenames to forward slashes |
||
| 582 | $data = preg_replace("/\\\\/", '/', $data); |
||
| 583 | |||
| 584 | $newrec .= ($newrec ? "\n" : '') . $level . ' ' . ($level === '0' && $xref ? $xref . ' ' : '') . $tag . ($data === '' && $tag !== 'NOTE' ? '' : ' ' . $data); |
||
| 585 | break; |
||
| 586 | case 'CONC': |
||
| 587 | // Merge CONC lines, to simplify access later on. |
||
| 588 | $newrec .= ($tree->getPreference('WORD_WRAPPED_NOTES') ? ' ' : '') . $data; |
||
| 589 | break; |
||
| 590 | } |
||
| 591 | } |
||
| 592 | |||
| 593 | return $newrec; |
||
| 594 | } |
||
| 595 | |||
| 596 | /** |
||
| 597 | * import record into database |
||
| 598 | * this function will parse the given gedcom record and add it to the database |
||
| 599 | * |
||
| 600 | * @param string $gedrec the raw gedcom record to parse |
||
| 601 | * @param Tree $tree import the record into this tree |
||
| 602 | * @param bool $update whether or not this is an updated record that has been accepted |
||
| 603 | * |
||
| 604 | * @return void |
||
| 605 | * @throws GedcomErrorException |
||
| 606 | */ |
||
| 607 | public static function importRecord($gedrec, Tree $tree, $update): void |
||
| 608 | { |
||
| 609 | $tree_id = $tree->id(); |
||
| 610 | |||
| 611 | // Escaped @ signs (only if importing from file) |
||
| 612 | if (!$update) { |
||
| 613 | $gedrec = str_replace('@@', '@', $gedrec); |
||
| 614 | } |
||
| 615 | |||
| 616 | // Standardise gedcom format |
||
| 617 | $gedrec = self::reformatRecord($gedrec, $tree); |
||
| 618 | |||
| 619 | // import different types of records |
||
| 620 | if (preg_match('/^0 @(' . Gedcom::REGEX_XREF . ')@ (' . Gedcom::REGEX_TAG . ')/', $gedrec, $match)) { |
||
| 621 | [, $xref, $type] = $match; |
||
| 622 | // check for a _UID, if the record doesn't have one, add one |
||
| 623 | if ($tree->getPreference('GENERATE_UIDS') && !strpos($gedrec, "\n1 _UID ")) { |
||
| 624 | $gedrec .= "\n1 _UID " . GedcomTag::createUid(); |
||
| 625 | } |
||
| 626 | } elseif (preg_match('/0 (HEAD|TRLR)/', $gedrec, $match)) { |
||
| 627 | $type = $match[1]; |
||
| 628 | $xref = $type; // For HEAD/TRLR, use type as pseudo XREF. |
||
| 629 | } else { |
||
| 630 | throw new GedcomErrorException($gedrec); |
||
| 631 | } |
||
| 632 | |||
| 633 | // If the user has downloaded their GEDCOM data (containing media objects) and edited it |
||
| 634 | // using an application which does not support (and deletes) media objects, then add them |
||
| 635 | // back in. |
||
| 636 | if ($tree->getPreference('keep_media') && $xref) { |
||
| 637 | $old_linked_media = DB::table('link') |
||
| 638 | ->where('l_from', '=', $xref) |
||
| 639 | ->where('l_file', '=', $tree_id) |
||
| 640 | ->where('l_type', '=', 'OBJE') |
||
| 641 | ->pluck('l_to'); |
||
| 642 | |||
| 643 | foreach ($old_linked_media as $media_id) { |
||
| 644 | $gedrec .= "\n1 OBJE @" . $media_id . '@'; |
||
| 645 | } |
||
| 646 | } |
||
| 647 | |||
| 648 | switch ($type) { |
||
| 649 | case 'INDI': |
||
| 650 | // Convert inline media into media objects |
||
| 651 | $gedrec = self::convertInlineMedia($tree, $gedrec); |
||
| 652 | |||
| 653 | $record = new Individual($xref, $gedrec, null, $tree); |
||
| 654 | if (preg_match('/\n1 RIN (.+)/', $gedrec, $match)) { |
||
| 655 | $rin = $match[1]; |
||
| 656 | } else { |
||
| 657 | $rin = $xref; |
||
| 658 | } |
||
| 659 | |||
| 660 | DB::table('individuals')->insert([ |
||
| 661 | 'i_id' => $xref, |
||
| 662 | 'i_file' => $tree_id, |
||
| 663 | 'i_rin' => $rin, |
||
| 664 | 'i_sex' => $record->sex(), |
||
| 665 | 'i_gedcom' => $gedrec, |
||
| 666 | ]); |
||
| 667 | |||
| 668 | // Update the cross-reference/index tables. |
||
| 669 | self::updatePlaces($xref, $tree, $gedrec); |
||
| 670 | self::updateDates($xref, $tree_id, $gedrec); |
||
| 671 | self::updateLinks($xref, $tree_id, $gedrec); |
||
| 672 | self::updateNames($xref, $tree_id, $record); |
||
| 673 | break; |
||
| 674 | case 'FAM': |
||
| 675 | // Convert inline media into media objects |
||
| 676 | $gedrec = self::convertInlineMedia($tree, $gedrec); |
||
| 677 | |||
| 678 | if (preg_match('/\n1 HUSB @(' . Gedcom::REGEX_XREF . ')@/', $gedrec, $match)) { |
||
| 679 | $husb = $match[1]; |
||
| 680 | } else { |
||
| 681 | $husb = ''; |
||
| 682 | } |
||
| 683 | if (preg_match('/\n1 WIFE @(' . Gedcom::REGEX_XREF . ')@/', $gedrec, $match)) { |
||
| 684 | $wife = $match[1]; |
||
| 685 | } else { |
||
| 686 | $wife = ''; |
||
| 687 | } |
||
| 688 | $nchi = preg_match_all('/\n1 CHIL @(' . Gedcom::REGEX_XREF . ')@/', $gedrec, $match); |
||
| 689 | if (preg_match('/\n1 NCHI (\d+)/', $gedrec, $match)) { |
||
| 690 | $nchi = max($nchi, $match[1]); |
||
| 691 | } |
||
| 692 | |||
| 693 | DB::table('families')->insert([ |
||
| 694 | 'f_id' => $xref, |
||
| 695 | 'f_file' => $tree_id, |
||
| 696 | 'f_husb' => $husb, |
||
| 697 | 'f_wife' => $wife, |
||
| 698 | 'f_gedcom' => $gedrec, |
||
| 699 | 'f_numchil' => $nchi, |
||
| 700 | ]); |
||
| 701 | |||
| 702 | // Update the cross-reference/index tables. |
||
| 703 | self::updatePlaces($xref, $tree, $gedrec); |
||
| 704 | self::updateDates($xref, $tree_id, $gedrec); |
||
| 705 | self::updateLinks($xref, $tree_id, $gedrec); |
||
| 706 | break; |
||
| 707 | case 'SOUR': |
||
| 708 | // Convert inline media into media objects |
||
| 709 | $gedrec = self::convertInlineMedia($tree, $gedrec); |
||
| 710 | |||
| 711 | $record = new Source($xref, $gedrec, null, $tree); |
||
| 712 | if (preg_match('/\n1 TITL (.+)/', $gedrec, $match)) { |
||
| 713 | $name = $match[1]; |
||
| 714 | } elseif (preg_match('/\n1 ABBR (.+)/', $gedrec, $match)) { |
||
| 715 | $name = $match[1]; |
||
| 716 | } else { |
||
| 717 | $name = $xref; |
||
| 718 | } |
||
| 719 | |||
| 720 | DB::table('sources')->insert([ |
||
| 721 | 's_id' => $xref, |
||
| 722 | 's_file' => $tree_id, |
||
| 723 | 's_name' => mb_substr($name, 0, 255), |
||
| 724 | 's_gedcom' => $gedrec, |
||
| 725 | ]); |
||
| 726 | |||
| 727 | // Update the cross-reference/index tables. |
||
| 728 | self::updateLinks($xref, $tree_id, $gedrec); |
||
| 729 | self::updateNames($xref, $tree_id, $record); |
||
| 730 | break; |
||
| 731 | case 'REPO': |
||
| 732 | // Convert inline media into media objects |
||
| 733 | $gedrec = self::convertInlineMedia($tree, $gedrec); |
||
| 734 | |||
| 735 | $record = new Repository($xref, $gedrec, null, $tree); |
||
| 736 | |||
| 737 | DB::table('other')->insert([ |
||
| 738 | 'o_id' => $xref, |
||
| 739 | 'o_file' => $tree_id, |
||
| 740 | 'o_type' => 'REPO', |
||
| 741 | 'o_gedcom' => $gedrec, |
||
| 742 | ]); |
||
| 743 | |||
| 744 | // Update the cross-reference/index tables. |
||
| 745 | self::updateLinks($xref, $tree_id, $gedrec); |
||
| 746 | self::updateNames($xref, $tree_id, $record); |
||
| 747 | break; |
||
| 748 | case 'NOTE': |
||
| 749 | $record = new Note($xref, $gedrec, null, $tree); |
||
| 750 | |||
| 751 | DB::table('other')->insert([ |
||
| 752 | 'o_id' => $xref, |
||
| 753 | 'o_file' => $tree_id, |
||
| 754 | 'o_type' => 'NOTE', |
||
| 755 | 'o_gedcom' => $gedrec, |
||
| 756 | ]); |
||
| 757 | |||
| 758 | // Update the cross-reference/index tables. |
||
| 759 | self::updateLinks($xref, $tree_id, $gedrec); |
||
| 760 | self::updateNames($xref, $tree_id, $record); |
||
| 761 | break; |
||
| 762 | case 'OBJE': |
||
| 763 | $record = new Media($xref, $gedrec, null, $tree); |
||
| 764 | |||
| 765 | DB::table('media')->insert([ |
||
| 766 | 'm_id' => $xref, |
||
| 767 | 'm_file' => $tree_id, |
||
| 768 | 'm_gedcom' => $gedrec, |
||
| 769 | ]); |
||
| 770 | |||
| 771 | foreach ($record->mediaFiles() as $media_file) { |
||
| 772 | DB::table('media_file')->insert([ |
||
| 773 | 'm_id' => $xref, |
||
| 774 | 'm_file' => $tree_id, |
||
| 775 | 'multimedia_file_refn' => mb_substr($media_file->filename(), 0, 248), |
||
| 776 | 'multimedia_format' => mb_substr($media_file->format(), 0, 4), |
||
| 777 | 'source_media_type' => mb_substr($media_file->type(), 0, 15), |
||
| 778 | 'descriptive_title' => mb_substr($media_file->title(), 0, 248), |
||
| 779 | ]); |
||
| 780 | } |
||
| 781 | |||
| 782 | // Update the cross-reference/index tables. |
||
| 783 | self::updateLinks($xref, $tree_id, $gedrec); |
||
| 784 | self::updateNames($xref, $tree_id, $record); |
||
| 785 | break; |
||
| 786 | default: // HEAD, TRLR, SUBM, SUBN, and custom record types. |
||
| 787 | // Force HEAD records to have a creation date. |
||
| 788 | if ($type === 'HEAD' && strpos($gedrec, "\n1 DATE ") === false) { |
||
| 789 | $gedrec .= "\n1 DATE " . date('j M Y'); |
||
| 790 | } |
||
| 791 | |||
| 792 | DB::table('other')->insert([ |
||
| 793 | 'o_id' => $xref, |
||
| 794 | 'o_file' => $tree_id, |
||
| 795 | 'o_type' => mb_substr($type, 0, 15), |
||
| 796 | 'o_gedcom' => $gedrec, |
||
| 797 | ]); |
||
| 798 | |||
| 799 | // Update the cross-reference/index tables. |
||
| 800 | self::updateLinks($xref, $tree_id, $gedrec); |
||
| 801 | break; |
||
| 802 | } |
||
| 803 | } |
||
| 804 | |||
| 805 | /** |
||
| 806 | * Extract all level 2 places from the given record and insert them into the places table |
||
| 807 | * |
||
| 808 | * @param string $xref |
||
| 809 | * @param Tree $tree |
||
| 810 | * @param string $gedrec |
||
| 811 | * |
||
| 812 | * @return void |
||
| 813 | */ |
||
| 814 | public static function updatePlaces(string $xref, Tree $tree, string $gedrec): void |
||
| 815 | { |
||
| 816 | preg_match_all('/^[2-9] PLAC (.+)/m', $gedrec, $matches); |
||
| 817 | |||
| 818 | $places = array_unique($matches[1]); |
||
| 819 | |||
| 820 | foreach ($places as $place_name) { |
||
| 821 | $place = new Place($place_name, $tree); |
||
| 822 | |||
| 823 | // Calling Place::id() will create the entry in the database, if it doesn't already exist. |
||
| 824 | // Link the place to the record |
||
| 825 | while ($place->id() !== 0) { |
||
| 826 | try { |
||
| 827 | DB::table('placelinks')->insert([ |
||
| 828 | 'pl_p_id' => $place->id(), |
||
| 829 | 'pl_gid' => $xref, |
||
| 830 | 'pl_file' => $tree->id(), |
||
| 831 | ]); |
||
| 832 | } catch (PDOException $ex) { |
||
| 833 | // Already linked this place - so presumably also any parent places. |
||
| 834 | break; |
||
| 835 | } |
||
| 836 | |||
| 837 | $place = $place->parent(); |
||
| 838 | } |
||
| 839 | } |
||
| 840 | } |
||
| 841 | |||
| 842 | /** |
||
| 843 | * Extract all the dates from the given record and insert them into the database. |
||
| 844 | * |
||
| 845 | * @param string $xref |
||
| 846 | * @param int $ged_id |
||
| 847 | * @param string $gedrec |
||
| 848 | * |
||
| 849 | * @return void |
||
| 850 | */ |
||
| 851 | public static function updateDates($xref, $ged_id, $gedrec): void |
||
| 852 | { |
||
| 853 | if (strpos($gedrec, '2 DATE ') && preg_match_all("/\n1 (\w+).*(?:\n[2-9].*)*(?:\n2 DATE (.+))(?:\n[2-9].*)*/", $gedrec, $matches, PREG_SET_ORDER)) { |
||
| 854 | foreach ($matches as $match) { |
||
| 855 | $fact = $match[1]; |
||
| 856 | if (($fact === 'FACT' || $fact === 'EVEN') && preg_match("/\n2 TYPE ([A-Z]{3,5})/", $match[0], $tmatch)) { |
||
| 857 | $fact = $tmatch[1]; |
||
| 858 | } |
||
| 859 | $date = new Date($match[2]); |
||
| 860 | DB::table('dates')->insert([ |
||
| 861 | 'd_day' => $date->minimumDate()->day, |
||
| 862 | 'd_month' => $date->minimumDate()->format('%O'), |
||
| 863 | 'd_mon' => $date->minimumDate()->month, |
||
| 864 | 'd_year' => $date->minimumDate()->year, |
||
| 865 | 'd_julianday1' => $date->minimumDate()->minimumJulianDay(), |
||
| 866 | 'd_julianday2' => $date->minimumDate()->maximumJulianDay(), |
||
| 867 | 'd_fact' => $fact, |
||
| 868 | 'd_gid' => $xref, |
||
| 869 | 'd_file' => $ged_id, |
||
| 870 | 'd_type' => $date->minimumDate()->format('%@'), |
||
| 871 | ]); |
||
| 872 | |||
| 873 | if ($date->minimumDate() !== $date->maximumDate()) { |
||
| 874 | DB::table('dates')->insert([ |
||
| 875 | 'd_day' => $date->maximumDate()->day, |
||
| 876 | 'd_month' => $date->maximumDate()->format('%O'), |
||
| 877 | 'd_mon' => $date->maximumDate()->month, |
||
| 878 | 'd_year' => $date->maximumDate()->year, |
||
| 879 | 'd_julianday1' => $date->maximumDate()->minimumJulianDay(), |
||
| 880 | 'd_julianday2' => $date->maximumDate()->maximumJulianDay(), |
||
| 881 | 'd_fact' => $fact, |
||
| 882 | 'd_gid' => $xref, |
||
| 883 | 'd_file' => $ged_id, |
||
| 884 | 'd_type' => $date->minimumDate()->format('%@'), |
||
| 885 | ]); |
||
| 886 | } |
||
| 887 | } |
||
| 888 | } |
||
| 889 | } |
||
| 890 | |||
| 891 | /** |
||
| 892 | * Extract all the links from the given record and insert them into the database |
||
| 893 | * |
||
| 894 | * @param string $xref |
||
| 895 | * @param int $ged_id |
||
| 896 | * @param string $gedrec |
||
| 897 | * |
||
| 898 | * @return void |
||
| 899 | */ |
||
| 900 | public static function updateLinks($xref, $ged_id, $gedrec): void |
||
| 901 | { |
||
| 902 | if (preg_match_all('/^\d+ (' . Gedcom::REGEX_TAG . ') @(' . Gedcom::REGEX_XREF . ')@/m', $gedrec, $matches, PREG_SET_ORDER)) { |
||
| 903 | $data = []; |
||
| 904 | foreach ($matches as $match) { |
||
| 905 | // Include each link once only. |
||
| 906 | if (!in_array($match[1] . $match[2], $data, true)) { |
||
| 907 | $data[] = $match[1] . $match[2]; |
||
| 908 | try { |
||
| 909 | DB::table('link')->insert([ |
||
| 910 | 'l_from' => $xref, |
||
| 911 | 'l_to' => $match[2], |
||
| 912 | 'l_type' => $match[1], |
||
| 913 | 'l_file' => $ged_id, |
||
| 914 | ]); |
||
| 915 | } catch (PDOException $ex) { |
||
| 916 | // Ignore any errors, which may be caused by "duplicates" that differ on case/collation, e.g. "S1" and "s1" |
||
| 917 | } |
||
| 918 | } |
||
| 919 | } |
||
| 920 | } |
||
| 921 | } |
||
| 922 | |||
| 923 | /** |
||
| 924 | * Extract all the names from the given record and insert them into the database. |
||
| 925 | * |
||
| 926 | * @param string $xref |
||
| 927 | * @param int $ged_id |
||
| 928 | * @param GedcomRecord $record |
||
| 929 | * |
||
| 930 | * @return void |
||
| 931 | */ |
||
| 932 | public static function updateNames($xref, $ged_id, GedcomRecord $record): void |
||
| 933 | { |
||
| 934 | foreach ($record->getAllNames() as $n => $name) { |
||
| 935 | if ($record instanceof Individual) { |
||
| 936 | if ($name['givn'] === '@P.N.') { |
||
| 937 | $soundex_givn_std = null; |
||
| 938 | $soundex_givn_dm = null; |
||
| 939 | } else { |
||
| 940 | $soundex_givn_std = Soundex::russell($name['givn']); |
||
| 941 | $soundex_givn_dm = Soundex::daitchMokotoff($name['givn']); |
||
| 942 | } |
||
| 943 | if ($name['surn'] === '@N.N.') { |
||
| 944 | $soundex_surn_std = null; |
||
| 945 | $soundex_surn_dm = null; |
||
| 946 | } else { |
||
| 947 | $soundex_surn_std = Soundex::russell($name['surname']); |
||
| 948 | $soundex_surn_dm = Soundex::daitchMokotoff($name['surname']); |
||
| 949 | } |
||
| 950 | DB::table('name')->insert([ |
||
| 951 | 'n_file' => $ged_id, |
||
| 952 | 'n_id' => $xref, |
||
| 953 | 'n_num' => $n, |
||
| 954 | 'n_type' => $name['type'], |
||
| 955 | 'n_sort' => mb_substr($name['sort'], 0, 255), |
||
| 956 | 'n_full' => mb_substr($name['fullNN'], 0, 255), |
||
| 957 | 'n_surname' => mb_substr($name['surname'], 0, 255), |
||
| 958 | 'n_surn' => mb_substr($name['surn'], 0, 255), |
||
| 959 | 'n_givn' => mb_substr($name['givn'], 0, 255), |
||
| 960 | 'n_soundex_givn_std' => $soundex_givn_std, |
||
| 961 | 'n_soundex_surn_std' => $soundex_surn_std, |
||
| 962 | 'n_soundex_givn_dm' => $soundex_givn_dm, |
||
| 963 | 'n_soundex_surn_dm' => $soundex_surn_dm, |
||
| 964 | ]); |
||
| 965 | } else { |
||
| 966 | DB::table('name')->insert([ |
||
| 967 | 'n_file' => $ged_id, |
||
| 968 | 'n_id' => $xref, |
||
| 969 | 'n_num' => $n, |
||
| 970 | 'n_type' => $name['type'], |
||
| 971 | 'n_sort' => mb_substr($name['sort'], 0, 255), |
||
| 972 | 'n_full' => mb_substr($name['fullNN'], 0, 255), |
||
| 973 | ]); |
||
| 974 | } |
||
| 975 | } |
||
| 976 | } |
||
| 977 | |||
| 978 | /** |
||
| 979 | * Extract inline media data, and convert to media objects. |
||
| 980 | * |
||
| 981 | * @param Tree $tree |
||
| 982 | * @param string $gedrec |
||
| 983 | * |
||
| 984 | * @return string |
||
| 985 | */ |
||
| 986 | public static function convertInlineMedia(Tree $tree, $gedrec): string |
||
| 999 | } |
||
| 1000 | |||
| 1001 | /** |
||
| 1002 | * Create a new media object, from inline media data. |
||
| 1003 | * |
||
| 1004 | * @param int $level |
||
| 1005 | * @param string $gedrec |
||
| 1006 | * @param Tree $tree |
||
| 1007 | * |
||
| 1008 | * @return string |
||
| 1009 | */ |
||
| 1010 | public static function createMediaObject($level, $gedrec, Tree $tree): string |
||
| 1071 | } |
||
| 1072 | |||
| 1073 | /** |
||
| 1074 | * update a record in the database |
||
| 1075 | * |
||
| 1076 | * @param string $gedrec |
||
| 1077 | * @param Tree $tree |
||
| 1078 | * @param bool $delete |
||
| 1079 | * |
||
| 1080 | * @return void |
||
| 1081 | * @throws GedcomErrorException |
||
| 1082 | */ |
||
| 1083 | public static function updateRecord($gedrec, Tree $tree, bool $delete): void |
||
| 1176 |
