| 1 | package AmberDB::Locale::Lang::gb; | ||
| 2 | |||
| 3 | use 5.016; | ||
| 4 | use warnings; | ||
| 5 | use utf8; | ||
| 6 | |||
| 7 | our $VERSION = '5.26.6'; | ||
| 8 | my $CREATED = '2026-09-03'; | ||
| 9 | |||
| 10 | # ------------------------------------------------------- | ||
| 11 | # Global Base (gb) Locale Data for AmberDB::Locale. | ||
| 12 | # | ||
| 13 | # Pure data module — no logic, no methods other than data(). | ||
| 14 | # | ||
| 15 | # Design Principles for Global Base (gb): | ||
| 16 | # 1. Universal Multilingual Support: Designed for international, | ||
| 17 | # cross-border datasets combining English, Turkish, German, | ||
| 18 | # French, Spanish, Italian, Scandinavian, and Slavic-Latin text. | ||
| 19 | # 2. Comprehensive Alphabet: alphabet_chars includes all European, | ||
| 20 | # Nordic, and Turkish extended Latin letters so no valid characters | ||
| 21 | # are stripped during text sanitization. | ||
| 22 | # 3. Permissive Search Regex: regex_map expands characters across their | ||
| 23 | # accented and unaccented forms (e.g. searching 'cafe' matches 'café', | ||
| 24 | # 'munchen' matches 'münchen', 'seker' matches 'şeker'). | ||
| 25 | # 4. Canonical Accent Folding: accent_map flattens accented letters | ||
| 26 | # to base Latin forms for high-recall inverted search indexing (.src). | ||
| 27 | # 5. Lossless ASCII Transliteration: ascii_map cleanly converts | ||
| 28 | # non-decomposable Unicode ligatures (ß->ss, æ->ae, œ->oe, ø->o, | ||
| 29 | # ı->i, ł->l, ð->d, þ->th, ə->e) for URL slugs and ASCII IDs. | ||
| 30 | # 6. International Formatting: Default numbers, dates, and currency | ||
| 31 | # follow ISO and international English conventions (USD/cent, . decimal). | ||
| 32 | # ------------------------------------------------------- | ||
| 33 | sub data { | ||
| 34 | return { | ||
| 35 | |||
| 36 | # --------------------------------------------------------- | ||
| 37 | # Casing special-cases | ||
| 38 | # uc_map: applied BEFORE Perl's uc() | ||
| 39 | # lc_map: applied BEFORE Perl's lc() | ||
| 40 | # Standard Unicode casing handles almost all Latin chars. | ||
| 41 | # Turkish dotted capital İ -> i is preserved during lc. | ||
| 42 | # --------------------------------------------------------- | ||
| 43 | uc_map => {}, | ||
| 44 | lc_map => { | ||
| 45 | "\x{130}" => 'i', # Turkish dotted capital İ -> i | ||
| 46 | }, | ||
| 47 | |||
| 48 | # --------------------------------------------------------- | ||
| 49 | # Case-insensitive & accent-tolerant search regex character map | ||
| 50 | # Maps both base and accented characters to a regex character class | ||
| 51 | # covering all regional variations. | ||
| 52 | # --------------------------------------------------------- | ||
| 53 | regex_map => { | ||
| 54 | # A variations: a, á, à, â, ä, ã, å, ā, æ | ||
| 55 | 'a' => '[aA\x{E1}\x{C1}\x{E0}\x{C0}\x{E2}\x{C2}\x{E4}\x{C4}\x{E3}\x{C3}\x{E5}\x{C5}\x{101}\x{100}\x{E6}\x{C6}]', | ||
| 56 | 'A' => '[aA\x{E1}\x{C1}\x{E0}\x{C0}\x{E2}\x{C2}\x{E4}\x{C4}\x{E3}\x{C3}\x{E5}\x{C5}\x{101}\x{100}\x{E6}\x{C6}]', | ||
| 57 | |||
| 58 | # C variations: c, ç, ć, č | ||
| 59 | 'c' => '[cC\x{E7}\x{C7}\x{107}\x{106}\x{10D}\x{10C}]', | ||
| 60 | 'C' => '[cC\x{E7}\x{C7}\x{107}\x{106}\x{10D}\x{10C}]', | ||
| 61 | "\x{E7}" => '[cC\x{E7}\x{C7}\x{107}\x{106}\x{10D}\x{10C}]', # ç | ||
| 62 | "\x{C7}" => '[cC\x{E7}\x{C7}\x{107}\x{106}\x{10D}\x{10C}]', # Ç | ||
| 63 | |||
| 64 | # D variations: d, ð, đ | ||
| 65 | 'd' => '[dD\x{F0}\x{D0}\x{111}\x{110}]', | ||
| 66 | 'D' => '[dD\x{F0}\x{D0}\x{111}\x{110}]', | ||
| 67 | |||
| 68 | # E variations: e, é, è, ê, ë, ē, ė, ę, ə | ||
| 69 | 'e' => '[eE\x{E9}\x{C9}\x{E8}\x{C8}\x{EA}\x{CA}\x{EB}\x{CB}\x{113}\x{112}\x{117}\x{116}\x{119}\x{118}\x{259}\x{18F}]', | ||
| 70 | 'E' => '[eE\x{E9}\x{C9}\x{E8}\x{C8}\x{EA}\x{CA}\x{EB}\x{CB}\x{113}\x{112}\x{117}\x{116}\x{119}\x{118}\x{259}\x{18F}]', | ||
| 71 | |||
| 72 | # G variations: g, ğ | ||
| 73 | 'g' => '[gG\x{11F}\x{11E}]', | ||
| 74 | 'G' => '[gG\x{11F}\x{11E}]', | ||
| 75 | "\x{11F}" => '[gG\x{11F}\x{11E}]', # ğ | ||
| 76 | "\x{11E}" => '[gG\x{11F}\x{11E}]', # Ğ | ||
| 77 | |||
| 78 | # I variations: i, I, ı, İ, î, ï, í, ì, ī | ||
| 79 | 'i' => '[iI\x{131}I\x{130}i\x{EE}\x{CE}\x{EF}\x{CF}\x{ED}\x{CD}\x{EC}\x{CC}\x{12B}\x{12A}]', | ||
| 80 | 'I' => '[iI\x{131}I\x{130}i\x{EE}\x{CE}\x{EF}\x{CF}\x{ED}\x{CD}\x{EC}\x{CC}\x{12B}\x{12A}]', | ||
| 81 | "\x{131}" => '[iI\x{131}I\x{130}i\x{EE}\x{CE}\x{EF}\x{CF}\x{ED}\x{CD}\x{EC}\x{CC}\x{12B}\x{12A}]', # ı | ||
| 82 | "\x{130}" => '[iI\x{131}I\x{130}i\x{EE}\x{CE}\x{EF}\x{CF}\x{ED}\x{CD}\x{EC}\x{CC}\x{12B}\x{12A}]', # İ | ||
| 83 | |||
| 84 | # L variations: l, ł | ||
| 85 | 'l' => '[lL\x{142}\x{141}]', | ||
| 86 | 'L' => '[lL\x{142}\x{141}]', | ||
| 87 | |||
| 88 | # N variations: n, ñ, ń | ||
| 89 | 'n' => '[nN\x{F1}\x{D1}\x{144}\x{143}]', | ||
| 90 | 'N' => '[nN\x{F1}\x{D1}\x{144}\x{143}]', | ||
| 91 | |||
| 92 | # O variations: o, ó, ò, ô, ö, õ, ø, ō, œ | ||
| 93 | 'o' => '[oO\x{F3}\x{D3}\x{F2}\x{D2}\x{F4}\x{D4}\x{F6}\x{D6}\x{F5}\x{D5}\x{F8}\x{D8}\x{14D}\x{14C}\x{153}\x{152}]', | ||
| 94 | 'O' => '[oO\x{F3}\x{D3}\x{F2}\x{D2}\x{F4}\x{D4}\x{F6}\x{D6}\x{F5}\x{D5}\x{F8}\x{D8}\x{14D}\x{14C}\x{153}\x{152}]', | ||
| 95 | "\x{F6}" => '[oO\x{F3}\x{D3}\x{F2}\x{D2}\x{F4}\x{D4}\x{F6}\x{D6}\x{F5}\x{D5}\x{F8}\x{D8}\x{14D}\x{14C}\x{153}\x{152}]', # ö | ||
| 96 | "\x{D6}" => '[oO\x{F3}\x{D3}\x{F2}\x{D2}\x{F4}\x{D4}\x{F6}\x{D6}\x{F5}\x{D5}\x{F8}\x{D8}\x{14D}\x{14C}\x{153}\x{152}]', # Ö | ||
| 97 | |||
| 98 | # S variations: s, ş, ś, š, ß | ||
| 99 | 's' => '[sS\x{15F}\x{15E}\x{15B}\x{15A}\x{161}\x{160}\x{DF}]', | ||
| 100 | 'S' => '[sS\x{15F}\x{15E}\x{15B}\x{15A}\x{161}\x{160}\x{DF}]', | ||
| 101 | "\x{15F}" => '[sS\x{15F}\x{15E}\x{15B}\x{15A}\x{161}\x{160}\x{DF}]', # ş | ||
| 102 | "\x{15E}" => '[sS\x{15F}\x{15E}\x{15B}\x{15A}\x{161}\x{160}\x{DF}]', # Ş | ||
| 103 | "\x{DF}" => '[sS\x{15F}\x{15E}\x{15B}\x{15A}\x{161}\x{160}\x{DF}]', # ß | ||
| 104 | |||
| 105 | # T variations: t, þ | ||
| 106 | 't' => '[tT\x{FE}\x{DE}]', | ||
| 107 | 'T' => '[tT\x{FE}\x{DE}]', | ||
| 108 | |||
| 109 | # U variations: u, ú, ù, û, ü, ū | ||
| 110 | 'u' => '[uU\x{FA}\x{DA}\x{F9}\x{D9}\x{FB}\x{DB}\x{FC}\x{DC}\x{16B}\x{16A}]', | ||
| 111 | 'U' => '[uU\x{FA}\x{DA}\x{F9}\x{D9}\x{FB}\x{DB}\x{FC}\x{DC}\x{16B}\x{16A}]', | ||
| 112 | "\x{FC}" => '[uU\x{FA}\x{DA}\x{F9}\x{D9}\x{FB}\x{DB}\x{FC}\x{DC}\x{16B}\x{16A}]', # ü | ||
| 113 | "\x{DC}" => '[uU\x{FA}\x{DA}\x{F9}\x{D9}\x{FB}\x{DB}\x{FC}\x{DC}\x{16B}\x{16A}]', # Ü | ||
| 114 | |||
| 115 | # Y variations: y, ý, ÿ | ||
| 116 | 'y' => '[yY\x{FD}\x{DD}\x{FF}]', | ||
| 117 | 'Y' => '[yY\x{FD}\x{DD}\x{FF}]', | ||
| 118 | |||
| 119 | # Z variations: z, ź, ż, ž | ||
| 120 | 'z' => '[zZ\x{17A}\x{179}\x{17C}\x{17B}\x{17E}\x{17D}]', | ||
| 121 | 'Z' => '[zZ\x{17A}\x{179}\x{17C}\x{17B}\x{17E}\x{17D}]', | ||
| 122 | }, | ||
| 123 | |||
| 124 | # --------------------------------------------------------- | ||
| 125 | # Phonetic assimilation & double-consonant reduction | ||
| 126 | # --------------------------------------------------------- | ||
| 127 | phonetic_map => [ | ||
| 128 | [ 'bb' => 'b' ], | ||
| 129 | [ 'dd' => 'd' ], | ||
| 130 | [ 'ff' => 'f' ], | ||
| 131 | [ 'gg' => 'g' ], | ||
| 132 | [ 'll' => 'l' ], | ||
| 133 | [ 'mm' => 'm' ], | ||
| 134 | [ 'nn' => 'n' ], | ||
| 135 | [ 'pp' => 'p' ], | ||
| 136 | [ 'rr' => 'r' ], | ||
| 137 | [ 'ss' => 's' ], | ||
| 138 | [ 'tt' => 't' ], | ||
| 139 | [ 'zz' => 'z' ], | ||
| 140 | ], | ||
| 141 | |||
| 142 | # --------------------------------------------------------- | ||
| 143 | # Optional custom sort collation overrides. | ||
| 144 | # Unicode::Collate handles standard UCA collation. | ||
| 145 | # --------------------------------------------------------- | ||
| 146 | sort_map => {}, | ||
| 147 | |||
| 148 | # --------------------------------------------------------- | ||
| 149 | # Alphabet character class for normalize() & safe string handling. | ||
| 150 | # Characters considered valid letters alongside standard a-zA-Z. | ||
| 151 | # Encompasses Latin-1 Supplement, Latin Extended-A, and Nordic/Turkish letters. | ||
| 152 | # --------------------------------------------------------- | ||
| 153 | alphabet_chars => | ||
| 154 | "\x{C0}\x{C1}\x{C2}\x{C3}\x{C4}\x{C5}\x{C6}\x{C7}\x{C8}\x{C9}\x{CA}\x{CB}" . | ||
| 155 | "\x{CC}\x{CD}\x{CE}\x{CF}\x{D0}\x{D1}\x{D2}\x{D3}\x{D4}\x{D5}\x{D6}\x{D8}" . | ||
| 156 | "\x{D9}\x{DA}\x{DB}\x{DC}\x{DD}\x{DE}\x{DF}" . | ||
| 157 | "\x{E0}\x{E1}\x{E2}\x{E3}\x{E4}\x{E5}\x{E6}\x{E7}\x{E8}\x{E9}\x{EA}\x{EB}" . | ||
| 158 | "\x{EC}\x{ED}\x{EE}\x{EF}\x{F0}\x{F1}\x{F2}\x{F3}\x{F4}\x{F5}\x{F6}\x{F8}" . | ||
| 159 | "\x{F9}\x{FA}\x{FB}\x{FC}\x{FD}\x{FE}\x{FF}" . | ||
| 160 | "\x{11E}\x{11F}\x{130}\x{131}\x{15E}\x{15F}" . # Ğ ğ İ ı Ş ş (Turkish/Azeri) | ||
| 161 | "\x{106}\x{107}\x{10C}\x{10D}\x{110}\x{111}" . # Ć ć Č č Đ đ (Slavic Latin) | ||
| 162 | "\x{141}\x{142}\x{143}\x{144}\x{15A}\x{15B}" . # Ł ł Ń ń Ś ś | ||
| 163 | "\x{160}\x{161}\x{179}\x{17A}\x{17B}\x{17C}\x{17D}\x{17E}" . # Š š Ź ź Ż ż Ž ž | ||
| 164 | "\x{152}\x{153}\x{18F}\x{259}", # Œ œ Ə ə (French / Azeri) | ||
| 165 | |||
| 166 | # --------------------------------------------------------- | ||
| 167 | # Accent normalization map — used by normalize(). | ||
| 168 | # Maps accented/regional characters to their clean base Latin forms. | ||
| 169 | # --------------------------------------------------------- | ||
| 170 | accent_map => { | ||
| 171 | # A / a | ||
| 172 | "\x{E0}" => 'a', "\x{E1}" => 'a', "\x{E2}" => 'a', "\x{E3}" => 'a', "\x{E4}" => 'a', "\x{E5}" => 'a', "\x{E6}" => 'ae', | ||
| 173 | "\x{C0}" => 'A', "\x{C1}" => 'A', "\x{C2}" => 'A', "\x{C3}" => 'A', "\x{C4}" => 'A', "\x{C5}" => 'A', "\x{C6}" => 'AE', | ||
| 174 | |||
| 175 | # C / c | ||
| 176 | "\x{E7}" => 'c', "\x{C7}" => 'C', # ç, Ç | ||
| 177 | "\x{107}" => 'c', "\x{106}" => 'C', # ć, Ć | ||
| 178 | "\x{10D}" => 'c', "\x{10C}" => 'C', # č, Č | ||
| 179 | |||
| 180 | # D / d | ||
| 181 | "\x{F0}" => 'd', "\x{D0}" => 'D', # ð, Ð | ||
| 182 | "\x{111}" => 'd', "\x{110}" => 'D', # đ, Đ | ||
| 183 | |||
| 184 | # E / e | ||
| 185 | "\x{E8}" => 'e', "\x{E9}" => 'e', "\x{EA}" => 'e', "\x{EB}" => 'e', | ||
| 186 | "\x{C8}" => 'E', "\x{C9}" => 'E', "\x{CA}" => 'E', "\x{CB}" => 'E', | ||
| 187 | "\x{259}" => 'e', "\x{18F}" => 'E', # ə, Ə | ||
| 188 | |||
| 189 | # G / g | ||
| 190 | "\x{11F}" => 'g', "\x{11E}" => 'G', # ğ, Ğ | ||
| 191 | |||
| 192 | # I / i | ||
| 193 | "\x{EC}" => 'i', "\x{ED}" => 'i', "\x{EE}" => 'i', "\x{EF}" => 'i', | ||
| 194 | "\x{CC}" => 'I', "\x{CD}" => 'I', "\x{CE}" => 'I', "\x{CF}" => 'I', | ||
| 195 | "\x{131}" => 'i', "\x{130}" => 'I', # ı, İ | ||
| 196 | |||
| 197 | # L / l | ||
| 198 | "\x{142}" => 'l', "\x{141}" => 'L', # ł, Ł | ||
| 199 | |||
| 200 | # N / n | ||
| 201 | "\x{F1}" => 'n', "\x{D1}" => 'N', # ñ, Ñ | ||
| 202 | "\x{144}" => 'n', "\x{143}" => 'N', # ń, Ń | ||
| 203 | |||
| 204 | # O / o | ||
| 205 | "\x{F2}" => 'o', "\x{F3}" => 'o', "\x{F4}" => 'o', "\x{F5}" => 'o', "\x{F6}" => 'o', "\x{F8}" => 'o', | ||
| 206 | "\x{D2}" => 'O', "\x{D3}" => 'O', "\x{D4}" => 'O', "\x{D5}" => 'O', "\x{D6}" => 'O', "\x{D8}" => 'O', | ||
| 207 | "\x{153}" => 'oe', "\x{152}" => 'OE', # œ, Œ | ||
| 208 | |||
| 209 | # S / s | ||
| 210 | "\x{15F}" => 's', "\x{15E}" => 'S', # ş, Ş | ||
| 211 | "\x{15B}" => 's', "\x{15A}" => 'S', # ś, Ś | ||
| 212 | "\x{161}" => 's', "\x{160}" => 'S', # š, Š | ||
| 213 | "\x{DF}" => 'ss', # ß | ||
| 214 | |||
| 215 | # T / t | ||
| 216 | "\x{FE}" => 'th', "\x{DE}" => 'TH', # þ, Þ | ||
| 217 | |||
| 218 | # U / u | ||
| 219 | "\x{F9}" => 'u', "\x{FA}" => 'u', "\x{FB}" => 'u', "\x{FC}" => 'u', | ||
| 220 | "\x{D9}" => 'U', "\x{DA}" => 'U', "\x{DB}" => 'U', "\x{DC}" => 'U', | ||
| 221 | |||
| 222 | # Y / y | ||
| 223 | "\x{FD}" => 'y', "\x{DD}" => 'Y', "\x{FF}" => 'y', | ||
| 224 | |||
| 225 | # Z / z | ||
| 226 | "\x{17A}" => 'z', "\x{179}" => 'Z', # ź, Ź | ||
| 227 | "\x{17C}" => 'z', "\x{17B}" => 'Z', # ż, Ż | ||
| 228 | "\x{17E}" => 'z', "\x{17D}" => 'Z', # ž, Ž | ||
| 229 | }, | ||
| 230 | |||
| 231 | # --------------------------------------------------------- | ||
| 232 | # ASCII transliteration pre-map — used BEFORE NFD in to_ascii(). | ||
| 233 | # Converts non-decomposable ligatures and special glyphs. | ||
| 234 | # --------------------------------------------------------- | ||
| 235 | ascii_map => { | ||
| 236 | "\x{DF}" => 'ss', # ß → ss | ||
| 237 | "\x{E6}" => 'ae', "\x{C6}" => 'AE',# æ → ae, Æ → AE | ||
| 238 | "\x{153}" => 'oe', "\x{152}" => 'OE',# œ → oe, Œ → OE | ||
| 239 | "\x{131}" => 'i', # ı → i | ||
| 240 | "\x{F0}" => 'd', "\x{D0}" => 'D', # ð → d, Ð → D | ||
| 241 | "\x{FE}" => 'th', "\x{DE}" => 'TH',# þ → th, Þ → TH | ||
| 242 | "\x{F8}" => 'o', "\x{D8}" => 'O', # ø → o, Ø → O | ||
| 243 | "\x{142}" => 'l', "\x{141}" => 'L', # ł → l, Ł → L | ||
| 244 | "\x{111}" => 'd', "\x{110}" => 'D', # đ → d, Đ → D | ||
| 245 | "\x{259}" => 'e', "\x{18F}" => 'E', # ə → e, Ə → E | ||
| 246 | }, | ||
| 247 | |||
| 248 | # --------------------------------------------------------- | ||
| 249 | # num2text number words (International English standard) | ||
| 250 | # --------------------------------------------------------- | ||
| 251 | numbers => { | ||
| 252 | zero => 'Zero', | ||
| 253 | negative => 'Minus', | ||
| 254 | ones => [qw(One Two Three Four Five Six Seven Eight Nine)], | ||
| 255 | tens => [qw(Ten Twenty Thirty Forty Fifty Sixty Seventy Eighty Ninety)], | ||
| 256 | hundred => 'Hundred', | ||
| 257 | thousand => 'Thousand', | ||
| 258 | million => 'Million', | ||
| 259 | billion => 'Billion', | ||
| 260 | currency => { main => 'USD', sub => 'cent' }, | ||
| 261 | decimal_sep => '.', | ||
| 262 | hundred_one_prefix => 1, # One Hundred | ||
| 263 | thousand_one_prefix => 1, # One Thousand | ||
| 264 | }, | ||
| 265 | |||
| 266 | # --------------------------------------------------------- | ||
| 267 | # HTML entity extras | ||
| 268 | # --------------------------------------------------------- | ||
| 269 | html_entities => {}, | ||
| 270 | |||
| 271 | # --------------------------------------------------------- | ||
| 272 | # Month and Day names (International English) | ||
| 273 | # --------------------------------------------------------- | ||
| 274 | months => [ | ||
| 275 | "January", "February", "March", "April", "May", "June", | ||
| 276 | "July", "August", "September", "October", "November", "December" | ||
| 277 | ], | ||
| 278 | days => [ | ||
| 279 | "Sunday", "Monday", "Tuesday", "Wednesday", | ||
| 280 | "Thursday", "Friday", "Saturday" | ||
| 281 | ], | ||
| 282 | |||
| 283 | # --------------------------------------------------------- | ||
| 284 | # Formatting metadata (number, currency, date) | ||
| 285 | # --------------------------------------------------------- | ||
| 286 | number_format => { | ||
| 287 | decimal_sep => '.', | ||
| 288 | group_sep => ',', | ||
| 289 | group_size => 3, | ||
| 290 | }, | ||
| 291 | }; | ||
| 292 | } | ||
| 293 | |||
| 294 | 1; | ||
| 295 | |||
| 296 | __END__ |