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 18declare(strict_types=1); 19 20namespace Fisharebest\Webtrees\Services; 21 22/** 23 * Utilities for manipulating GEDCOM data. 24 */ 25class GedcomService 26{ 27 // Gedcom allows 255 characters (not bytes), including the EOL character. 28 private const EOL = "\r\n"; 29 private const EOL_REGEX = '\r|\r\n|\n|\n\r'; 30 private const LINE_LENGTH = 255 - 2; 31 32 33 // User defined tags begin with an underscore 34 private const USER_DEFINED_TAG_PREFIX = '_'; 35 36 // Some applications, such as FTM, use GEDCOM tag names instead of the tags. 37 private const TAG_NAMES = [ 38 'ABBREVIATION' => 'ABBR', 39 'ADDRESS' => 'ADDR', 40 'ADDRESS1' => 'ADR1', 41 'ADDRESS2' => 'ADR2', 42 'ADOPTION' => 'ADOP', 43 'AFN' => 'AFN', 44 'AGE' => 'AGE', 45 'AGENCY' => 'AGNC', 46 'ALIAS' => 'ALIA', 47 'ANCESTORS' => 'ANCE', 48 'ANCES_INTEREST' => 'ANCI', 49 'ANULMENT' => 'ANUL', 50 'ASSOCIATES' => 'ASSO', 51 'AUTHOR' => 'AUTH', 52 'BAPTISM-LDS' => 'BAPL', 53 'BAPTISM' => 'BAPM', 54 'BAR_MITZVAH' => 'BARM', 55 'BAS_MITZVAH' => 'BASM', 56 'BIRTH' => 'BIRT', 57 'BLESSING' => 'BLES', 58 'BURIAL' => 'BURI', 59 'CALL_NUMBER' => 'CALN', 60 'CASTE' => 'CAST', 61 'CAUSE' => 'CAUS', 62 'CENSUS' => 'CENS', 63 'CHANGE' => 'CHAN', 64 'CHARACTER' => 'CHAR', 65 'CHILD' => 'CHIL', 66 'CHRISTENING' => 'CHR', 67 'ADULT_CHRISTENING' => 'CHRA', 68 'CITY' => 'CITY', 69 'CONCATENATION' => 'CONC', 70 'CONFIRMATION' => 'CONF', 71 'CONFIRMATION-LDS' => 'CONL', 72 'CONTINUED' => 'CONT', 73 'COPYRIGHT' => 'COPY', 74 'CORPORTATE' => 'CORP', 75 'CREMATION' => 'CREM', 76 'COUNTRY' => 'CTRY', 77 'DATA' => 'DATA', 78 'DATE' => 'DATE', 79 'DEATH' => 'DEAT', 80 'DESCENDANTS' => 'DESC', 81 'DESCENDANTS_INT' => 'DESI', 82 'DESTINATION' => 'DEST', 83 'DIVORCE' => 'DIV', 84 'DIVORCE_FILED' => 'DIVF', 85 'PHY_DESCRIPTION' => 'DSCR', 86 'EDUCATION' => 'EDUC', 87 'EMAIL' => 'EMAI', 88 'EMIGRATION' => 'EMIG', 89 'ENDOWMENT' => 'ENDL', 90 'ENGAGEMENT' => 'ENGA', 91 'EVENT' => 'EVEN', 92 'FACT' => 'FACT', 93 'FAMILY' => 'FAM', 94 'FAMILY_CHILD' => 'FAMC', 95 'FAMILY_FILE' => 'FAMF', 96 'FAMILY_SPOUSE' => 'FAMS', 97 'FACIMILIE' => 'FAX', 98 'FIRST_COMMUNION' => 'FCOM', 99 'FILE' => 'FILE', 100 'FORMAT' => 'FORM', 101 'PHONETIC' => 'FONE', 102 'GEDCOM' => 'GEDC', 103 'GIVEN_NAME' => 'GIVN', 104 'GRADUATION' => 'GRAD', 105 'HEADER' => 'HEAD', 106 'HUSBAND' => 'HUSB', 107 'IDENT_NUMBER' => 'IDNO', 108 'IMMIGRATION' => 'IMMI', 109 'INDIVIDUAL' => 'INDI', 110 'LANGUAGE' => 'LANG', 111 'LATITUDE' => 'LATI', 112 'LONGITUDE' => 'LONG', 113 'MAP' => 'MAP', 114 'MARRIAGE_BANN' => 'MARB', 115 'MARR_CONTRACT' => 'MARC', 116 'MARR_LICENSE' => 'MARL', 117 'MARRIAGE' => 'MARR', 118 'MEDIA' => 'MEDI', 119 'NAME' => 'NAME', 120 'NATIONALITY' => 'NATI', 121 'NATURALIZATION' => 'NATU', 122 'CHILDREN_COUNT' => 'NCHI', 123 'NICKNAME' => 'NICK', 124 'MARRIAGE_COUNT' => 'NMR', 125 'NOTE' => 'NOTE', 126 'NAME_PREFIX' => 'NPFX', 127 'NAME_SUFFIX' => 'NSFX', 128 'OBJECT' => 'OBJE', 129 'OCCUPATION' => 'OCCU', 130 'ORDINANCE' => 'ORDI', 131 'ORDINATION' => 'ORDN', 132 'PAGE' => 'PAGE', 133 'PEDIGREE' => 'PEDI', 134 'PHONE' => 'PHON', 135 'PLACE' => 'PLAC', 136 'POSTAL_CODE' => 'POST', 137 'PROBATE' => 'PROB', 138 'PROPERTY' => 'PROP', 139 'PUBLICATION' => 'PUBL', 140 'QUALITY_OF_DATA' => 'QUAY', 141 'REFERENCE' => 'REFN', 142 'RELATIONSHIP' => 'RELA', 143 'RELIGION' => 'RELI', 144 'REPOSITORY' => 'REPO', 145 'RESIDENCE' => 'RESI', 146 'RESTRICTION' => 'RESN', 147 'RETIREMENT' => 'RETI', 148 'REC_FILE_NUMBER' => 'RFN', 149 'REC_ID_NUMBER' => 'RIN', 150 'ROLE' => 'ROLE', 151 'ROMANIZED' => 'ROMN', 152 'SEALING_CHILD' => 'SLGC', 153 'SEALING_SPOUSE' => 'SLGS', 154 'SEX' => 'SEX', 155 'SOURCE' => 'SOUR', 156 'SURN_PREFIX' => 'SPFX', 157 'SOC_SEC_NUMBER' => 'SSN', 158 'STATE' => 'STAE', 159 'STATUS' => 'STAT', 160 'SUBMITTER' => 'SUBM', 161 'SUBMISSION' => 'SUBN', 162 'SURNAME' => 'SURN', 163 'TEMPLE' => 'TEMP', 164 'TEXT' => 'TEXT', 165 'TIME' => 'TIME', 166 'TITLE' => 'TITL', 167 'TRAILER' => 'TRLR', 168 'TYPE' => 'TYPE', 169 'VERSION' => 'VERS', 170 'WIFE' => 'WIFE', 171 'WILL' => 'WILL', 172 'WEB' => 'WWW', 173 '_DEATH_OF_SPOUSE' => 'DETS', 174 '_DEGREE' => '_DEG', 175 '_FILE' => 'FILE', 176 '_MEDICAL' => '_MCL', 177 '_MILITARY_SERVICE' => '_MILT', 178 ]; 179 180 // Custom tags used by other applications, with direct synonyms 181 private const TAG_SYNONYMS = [ 182 ]; 183 184 // LATI and LONG tags 185 private const DEGREE_FORMAT = ' % .5f%s'; 186 private const LATITUDE_NORTH = 'N'; 187 private const LATITUDE_SOUTH = 'S'; 188 private const LONGITUDE_EAST = 'E'; 189 private const LONGITUDE_WEST = 'W'; 190 191 // PLAC tags 192 private const PLACE_SEPARATOR = ', '; 193 private const PLACE_SEPARATOR_REGEX = ' *, *'; 194 195 // SEX tags 196 private const SEX_FEMALE = 'F'; 197 private const SEX_MALE = 'M'; 198 private const SEX_UNKNOWN = 'U'; 199 200 /** 201 * Convert a GEDCOM tag to a canonical form. 202 * 203 * @param string $tag 204 * 205 * @return string 206 */ 207 public function canonicalTag(string $tag): string 208 { 209 $tag = strtoupper($tag); 210 211 $tag = self::TAG_NAMES[$tag] ?? self::TAG_SYNONYMS[$tag] ?? $tag; 212 213 return $tag; 214 } 215 216 /** 217 * @param string $tag 218 * 219 * @return bool 220 */ 221 public function isUserDefinedTag(string $tag): bool 222 { 223 return substr_compare($tag, self::USER_DEFINED_TAG_PREFIX, 0, 1) === 0; 224 } 225 226 /** 227 * @param string $text 228 * 229 * @return float 230 */ 231 public function readLatitude(string $text): float 232 { 233 return $this->readDegrees($text, self::LATITUDE_NORTH, self::LATITUDE_SOUTH); 234 } 235 236 /** 237 * @param string $text 238 * 239 * @return float 240 */ 241 public function readLongitude(string $text): float 242 { 243 return $this->readDegrees($text, self::LONGITUDE_EAST, self::LONGITUDE_WEST); 244 } 245 246 /** 247 * @param string $text 248 * @param string $positive 249 * @param string $negative 250 * 251 * @return float 252 */ 253 private function readDegrees(string $text, string $positive, string $negative): float 254 { 255 $text = trim($text); 256 $hemisphere = substr($text, 0, 1); 257 $degrees = substr($text, 1); 258 259 // Match a valid GEDCOM format 260 if (is_numeric($degrees)) { 261 $hemisphere = strtoupper($hemisphere); 262 $degrees = (float) $degrees; 263 264 if ($hemisphere === $positive) { 265 return $degrees; 266 } 267 268 if ($hemisphere === $negative) { 269 return -$degrees; 270 } 271 } 272 273 // Just a number? 274 if (is_numeric($text)) { 275 return (float) $text; 276 } 277 278 // Can't match anything. 279 return 0.0; 280 } 281 282 /** 283 * @param float $latitude 284 * 285 * @return string 286 */ 287 public function writeLatitude(float $latitude): string 288 { 289 return $this->writeDegrees($latitude, self::LATITUDE_NORTH, self::LATITUDE_SOUTH); 290 } 291 292 /** 293 * @param float $longitude 294 * 295 * @return string 296 */ 297 public function writeLongitude(float $longitude): string 298 { 299 return $this->writeDegrees($longitude, self::LONGITUDE_EAST, self::LONGITUDE_WEST); 300 } 301 302 /** 303 * @param float $degrees 304 * @param string $positive 305 * @param string $negative 306 * 307 * @return string 308 */ 309 private function writeDegrees(float $degrees, string $positive, string $negative): string 310 { 311 if ($degrees < 0.0) { 312 return sprintf(self::DEGREE_FORMAT, $degrees, $negative); 313 } 314 315 return sprintf(self::DEGREE_FORMAT, $degrees, $positive); 316 } 317 318 /** 319 * Although empty placenames are valid "Town, , Country", it is only meaningful 320 * when structured places are used (PLAC:FORM town, county, country), and 321 * structured places are discouraged. 322 * 323 * @param string $text 324 * 325 * @return string[] 326 */ 327 public function readPlace(string $text): array 328 { 329 $text = trim($text); 330 331 return preg_split(self::PLACE_SEPARATOR_REGEX, $text, PREG_SPLIT_NO_EMPTY); 332 } 333 334 /** 335 * @param string[] $place 336 * 337 * @return string 338 */ 339 public function writePlace(array $place): string 340 { 341 return implode(self::PLACE_SEPARATOR, $place); 342 } 343 344 /** 345 * Some applications use non-standard values for unknown. 346 * 347 * @param string $text 348 * 349 * @return string 350 */ 351 public function readSex(string $text): string 352 { 353 $text = strtoupper($text); 354 355 if ($text !== self::SEX_MALE && $text !== self::SEX_FEMALE) { 356 $text = self::SEX_UNKNOWN; 357 } 358 359 return $text; 360 } 361} 362