summaryrefslogtreecommitdiff
path: root/core/string
diff options
context:
space:
mode:
Diffstat (limited to 'core/string')
-rw-r--r--core/string/char_utils.h92
-rw-r--r--core/string/locales.h1197
-rw-r--r--core/string/node_path.cpp6
-rw-r--r--core/string/node_path.h4
-rw-r--r--core/string/optimized_translation.cpp4
-rw-r--r--core/string/optimized_translation.h6
-rw-r--r--core/string/print_string.cpp4
-rw-r--r--core/string/print_string.h4
-rw-r--r--core/string/string_buffer.h4
-rw-r--r--core/string/string_builder.cpp6
-rw-r--r--core/string/string_builder.h4
-rw-r--r--core/string/string_name.cpp39
-rw-r--r--core/string/string_name.h16
-rw-r--r--core/string/translation.cpp1241
-rw-r--r--core/string/translation.h40
-rw-r--r--core/string/translation_po.cpp4
-rw-r--r--core/string/translation_po.h4
-rw-r--r--core/string/ucaps.h4
-rw-r--r--core/string/ustring.cpp345
-rw-r--r--core/string/ustring.h32
20 files changed, 1841 insertions, 1215 deletions
diff --git a/core/string/char_utils.h b/core/string/char_utils.h
new file mode 100644
index 0000000000..0afd058f01
--- /dev/null
+++ b/core/string/char_utils.h
@@ -0,0 +1,92 @@
+/*************************************************************************/
+/* char_utils.h */
+/*************************************************************************/
+/* This file is part of: */
+/* GODOT ENGINE */
+/* https://godotengine.org */
+/*************************************************************************/
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
+/* */
+/* Permission is hereby granted, free of charge, to any person obtaining */
+/* a copy of this software and associated documentation files (the */
+/* "Software"), to deal in the Software without restriction, including */
+/* without limitation the rights to use, copy, modify, merge, publish, */
+/* distribute, sublicense, and/or sell copies of the Software, and to */
+/* permit persons to whom the Software is furnished to do so, subject to */
+/* the following conditions: */
+/* */
+/* The above copyright notice and this permission notice shall be */
+/* included in all copies or substantial portions of the Software. */
+/* */
+/* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, */
+/* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF */
+/* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.*/
+/* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY */
+/* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, */
+/* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE */
+/* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */
+/*************************************************************************/
+
+#ifndef CHAR_UTILS_H
+#define CHAR_UTILS_H
+
+#include "core/typedefs.h"
+
+static _FORCE_INLINE_ bool is_ascii_upper_case(char32_t c) {
+ return (c >= 'A' && c <= 'Z');
+}
+
+static _FORCE_INLINE_ bool is_ascii_lower_case(char32_t c) {
+ return (c >= 'a' && c <= 'z');
+}
+
+static _FORCE_INLINE_ bool is_digit(char32_t c) {
+ return (c >= '0' && c <= '9');
+}
+
+static _FORCE_INLINE_ bool is_hex_digit(char32_t c) {
+ return (is_digit(c) || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'));
+}
+
+static _FORCE_INLINE_ bool is_binary_digit(char32_t c) {
+ return (c == '0' || c == '1');
+}
+
+static _FORCE_INLINE_ bool is_ascii_char(char32_t c) {
+ return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
+}
+
+static _FORCE_INLINE_ bool is_ascii_alphanumeric_char(char32_t c) {
+ return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9');
+}
+
+static _FORCE_INLINE_ bool is_ascii_identifier_char(char32_t c) {
+ return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_';
+}
+
+static _FORCE_INLINE_ bool is_symbol(char32_t c) {
+ return c != '_' && ((c >= '!' && c <= '/') || (c >= ':' && c <= '@') || (c >= '[' && c <= '`') || (c >= '{' && c <= '~') || c == '\t' || c == ' ');
+}
+
+static _FORCE_INLINE_ bool is_control(char32_t p_char) {
+ return (p_char <= 0x001f) || (p_char >= 0x007f && p_char <= 0x009f);
+}
+
+static _FORCE_INLINE_ bool is_whitespace(char32_t p_char) {
+ return (p_char == ' ') || (p_char == 0x00a0) || (p_char == 0x1680) || (p_char >= 0x2000 && p_char <= 0x200a) || (p_char == 0x202f) || (p_char == 0x205f) || (p_char == 0x3000) || (p_char == 0x2028) || (p_char == 0x2029) || (p_char >= 0x0009 && p_char <= 0x000d) || (p_char == 0x0085);
+}
+
+static _FORCE_INLINE_ bool is_linebreak(char32_t p_char) {
+ return (p_char >= 0x000a && p_char <= 0x000d) || (p_char == 0x0085) || (p_char == 0x2028) || (p_char == 0x2029);
+}
+
+static _FORCE_INLINE_ bool is_punct(char32_t p_char) {
+ return (p_char >= ' ' && p_char <= '/') || (p_char >= ':' && p_char <= '@') || (p_char >= '[' && p_char <= '^') || (p_char == '`') || (p_char >= '{' && p_char <= '~') || (p_char >= 0x2000 && p_char <= 0x206f) || (p_char >= 0x3000 && p_char <= 0x303f);
+}
+
+static _FORCE_INLINE_ bool is_underscore(char32_t p_char) {
+ return (p_char == '_');
+}
+
+#endif // CHAR_UTILS_H
diff --git a/core/string/locales.h b/core/string/locales.h
new file mode 100644
index 0000000000..32d6608ec2
--- /dev/null
+++ b/core/string/locales.h
@@ -0,0 +1,1197 @@
+/*************************************************************************/
+/* locales.h */
+/*************************************************************************/
+/* This file is part of: */
+/* GODOT ENGINE */
+/* https://godotengine.org */
+/*************************************************************************/
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
+/* */
+/* Permission is hereby granted, free of charge, to any person obtaining */
+/* a copy of this software and associated documentation files (the */
+/* "Software"), to deal in the Software without restriction, including */
+/* without limitation the rights to use, copy, modify, merge, publish, */
+/* distribute, sublicense, and/or sell copies of the Software, and to */
+/* permit persons to whom the Software is furnished to do so, subject to */
+/* the following conditions: */
+/* */
+/* The above copyright notice and this permission notice shall be */
+/* included in all copies or substantial portions of the Software. */
+/* */
+/* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, */
+/* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF */
+/* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.*/
+/* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY */
+/* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, */
+/* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE */
+/* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */
+/*************************************************************************/
+
+#ifndef LOCALES_H
+#define LOCALES_H
+
+// Windows has some weird locale identifiers which do not honor the ISO 639-1
+// standardized nomenclature. Whenever those don't conflict with existing ISO
+// identifiers, we override them.
+//
+// Reference:
+// - https://msdn.microsoft.com/en-us/library/windows/desktop/ms693062(v=vs.85).aspx
+
+static const char *locale_renames[][2] = {
+ { "in", "id" }, // Indonesian
+ { "iw", "he" }, // Hebrew
+ { "no", "nb" }, // Norwegian Bokmål
+ { "C", "en" }, // Locale is not set, fallback to English.
+ { nullptr, nullptr }
+};
+
+// Additional script information to preferred scripts.
+// Language code, script code, default country, supported countries.
+// Reference:
+// - https://lh.2xlibre.net/locales/
+// - https://www.localeplanet.com/icu/index.html
+// - https://docs.microsoft.com/en-us/openspecs/windows_protocols/ms-lcid/70feba9f-294e-491e-b6eb-56532684c37f
+
+static const char *locale_scripts[][4] = {
+ { "az", "Latn", "", "AZ" },
+ { "az", "Arab", "", "IR" },
+ { "bs", "Latn", "", "BA" },
+ { "ff", "Latn", "", "BF,CM,GH,GM,GN,GW,LR,MR,NE,NG,SL,SN" },
+ { "pa", "Arab", "PK", "PK" },
+ { "pa", "Guru", "IN", "IN" },
+ { "sd", "Arab", "PK", "PK" },
+ { "sd", "Deva", "IN", "IN" },
+ { "shi", "Tfng", "", "MA" },
+ { "sr", "Cyrl", "", "BA,RS,XK" },
+ { "sr", "Latn", "", "ME" },
+ { "uz", "Latn", "", "UZ" },
+ { "uz", "Arab", "AF", "AF" },
+ { "vai", "Vaii", "", "LR" },
+ { "yue", "Hans", "CN", "CN" },
+ { "yue", "Hant", "HK", "HK" },
+ { "zh", "Hans", "CN", "CN,SG" },
+ { "zh", "Hant", "TW", "HK,MO,TW" },
+ { nullptr, nullptr, nullptr, nullptr }
+};
+
+// Additional mapping for outdated, temporary or exceptionally reserved country codes.
+// Reference:
+// - https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2
+// - https://www.iso.org/obp/ui/#search/code/
+
+static const char *country_renames[][2] = {
+ { "BU", "MM" }, // Burma, name changed to Myanmar.
+ { "KV", "XK" }, // Kosovo (temporary FIPS code to European Commission code), no official ISO code assigned.
+ { "TP", "TL" }, // East Timor, name changed to Timor-Leste.
+ { "UK", "GB" }, // United Kingdom, exceptionally reserved code.
+ { nullptr, nullptr }
+};
+
+// Country code, country name.
+// Reference:
+// - https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2
+// - https://www.iso.org/obp/ui/#search/code/
+
+static const char *country_names[][2] = {
+ { "AC", "Ascension Island" }, // Exceptionally reserved.
+ { "AD", "Andorra" },
+ { "AE", "United Arab Emirates" },
+ { "AF", "Afghanistan" },
+ { "AG", "Antigua and Barbuda" },
+ { "AI", "Anguilla" },
+ { "AL", "Albania" },
+ { "AM", "Armenia" },
+ { "AN", "Netherlands Antilles" }, // Transitionally reserved, divided into BQ, CW and SX.
+ { "AO", "Angola" },
+ { "AQ", "Antarctica" },
+ { "AR", "Argentina" },
+ { "AS", "American Samoa" },
+ { "AT", "Austria" },
+ { "AU", "Australia" },
+ { "AW", "Aruba" },
+ { "AX", "Åland Islands" },
+ { "AZ", "Azerbaijan" },
+ { "BA", "Bosnia and Herzegovina" },
+ { "BB", "Barbados" },
+ { "BD", "Bangladesh" },
+ { "BE", "Belgium" },
+ { "BF", "Burkina Faso" },
+ { "BG", "Bulgaria" },
+ { "BH", "Bahrain" },
+ { "BI", "Burundi" },
+ { "BJ", "Benin" },
+ { "BL", "St. Barthélemy" },
+ { "BM", "Bermuda" },
+ { "BN", "Brunei" },
+ { "BO", "Bolivia" },
+ { "BQ", "Caribbean Netherlands" },
+ { "BR", "Brazil" },
+ { "BS", "Bahamas" },
+ { "BT", "Bhutan" },
+ { "BV", "Bouvet Island" },
+ { "BW", "Botswana" },
+ { "BY", "Belarus" },
+ { "BZ", "Belize" },
+ { "CA", "Canada" },
+ { "CC", "Cocos (Keeling) Islands" },
+ { "CD", "Congo - Kinshasa" },
+ { "CF", "Central African Republic" },
+ { "CG", "Congo - Brazzaville" },
+ { "CH", "Switzerland" },
+ { "CI", "Côte d'Ivoire" },
+ { "CK", "Cook Islands" },
+ { "CL", "Chile" },
+ { "CM", "Cameroon" },
+ { "CN", "China" },
+ { "CO", "Colombia" },
+ { "CP", "Clipperton Island" }, // Exceptionally reserved.
+ { "CR", "Costa Rica" },
+ { "CQ", "Island of Sark" }, // Exceptionally reserved.
+ { "CU", "Cuba" },
+ { "CV", "Cabo Verde" },
+ { "CW", "Curaçao" },
+ { "CX", "Christmas Island" },
+ { "CY", "Cyprus" },
+ { "CZ", "Czechia" },
+ { "DE", "Germany" },
+ { "DG", "Diego Garcia" }, // Exceptionally reserved.
+ { "DJ", "Djibouti" },
+ { "DK", "Denmark" },
+ { "DM", "Dominica" },
+ { "DO", "Dominican Republic" },
+ { "DZ", "Algeria" },
+ { "EA", "Ceuta and Melilla" }, // Exceptionally reserved.
+ { "EC", "Ecuador" },
+ { "EE", "Estonia" },
+ { "EG", "Egypt" },
+ { "EH", "Western Sahara" },
+ { "ER", "Eritrea" },
+ { "ES", "Spain" },
+ { "ET", "Ethiopia" },
+ { "EU", "European Union" }, // Exceptionally reserved.
+ { "EZ", "Eurozone" }, // Exceptionally reserved.
+ { "FI", "Finland" },
+ { "FJ", "Fiji" },
+ { "FK", "Falkland Islands" },
+ { "FM", "Micronesia" },
+ { "FO", "Faroe Islands" },
+ { "FR", "France" },
+ { "FX", "France, Metropolitan" }, // Exceptionally reserved.
+ { "GA", "Gabon" },
+ { "GB", "United Kingdom" },
+ { "GD", "Grenada" },
+ { "GE", "Georgia" },
+ { "GF", "French Guiana" },
+ { "GG", "Guernsey" },
+ { "GH", "Ghana" },
+ { "GI", "Gibraltar" },
+ { "GL", "Greenland" },
+ { "GM", "Gambia" },
+ { "GN", "Guinea" },
+ { "GP", "Guadeloupe" },
+ { "GQ", "Equatorial Guinea" },
+ { "GR", "Greece" },
+ { "GS", "South Georgia and South Sandwich Islands" },
+ { "GT", "Guatemala" },
+ { "GU", "Guam" },
+ { "GW", "Guinea-Bissau" },
+ { "GY", "Guyana" },
+ { "HK", "Hong Kong" },
+ { "HM", "Heard Island and McDonald Islands" },
+ { "HN", "Honduras" },
+ { "HR", "Croatia" },
+ { "HT", "Haiti" },
+ { "HU", "Hungary" },
+ { "IC", "Canary Islands" }, // Exceptionally reserved.
+ { "ID", "Indonesia" },
+ { "IE", "Ireland" },
+ { "IL", "Israel" },
+ { "IM", "Isle of Man" },
+ { "IN", "India" },
+ { "IO", "British Indian Ocean Territory" },
+ { "IQ", "Iraq" },
+ { "IR", "Iran" },
+ { "IS", "Iceland" },
+ { "IT", "Italy" },
+ { "JE", "Jersey" },
+ { "JM", "Jamaica" },
+ { "JO", "Jordan" },
+ { "JP", "Japan" },
+ { "KE", "Kenya" },
+ { "KG", "Kyrgyzstan" },
+ { "KH", "Cambodia" },
+ { "KI", "Kiribati" },
+ { "KM", "Comoros" },
+ { "KN", "St. Kitts and Nevis" },
+ { "KP", "North Korea" },
+ { "KR", "South Korea" },
+ { "KW", "Kuwait" },
+ { "KY", "Cayman Islands" },
+ { "KZ", "Kazakhstan" },
+ { "LA", "Laos" },
+ { "LB", "Lebanon" },
+ { "LC", "St. Lucia" },
+ { "LI", "Liechtenstein" },
+ { "LK", "Sri Lanka" },
+ { "LR", "Liberia" },
+ { "LS", "Lesotho" },
+ { "LT", "Lithuania" },
+ { "LU", "Luxembourg" },
+ { "LV", "Latvia" },
+ { "LY", "Libya" },
+ { "MA", "Morocco" },
+ { "MC", "Monaco" },
+ { "MD", "Moldova" },
+ { "ME", "Montenegro" },
+ { "MF", "St. Martin" },
+ { "MG", "Madagascar" },
+ { "MH", "Marshall Islands" },
+ { "MK", "North Macedonia" },
+ { "ML", "Mali" },
+ { "MM", "Myanmar" },
+ { "MN", "Mongolia" },
+ { "MO", "Macao" },
+ { "MP", "Northern Mariana Islands" },
+ { "MQ", "Martinique" },
+ { "MR", "Mauritania" },
+ { "MS", "Montserrat" },
+ { "MT", "Malta" },
+ { "MU", "Mauritius" },
+ { "MV", "Maldives" },
+ { "MW", "Malawi" },
+ { "MX", "Mexico" },
+ { "MY", "Malaysia" },
+ { "MZ", "Mozambique" },
+ { "NA", "Namibia" },
+ { "NC", "New Caledonia" },
+ { "NE", "Niger" },
+ { "NF", "Norfolk Island" },
+ { "NG", "Nigeria" },
+ { "NI", "Nicaragua" },
+ { "NL", "Netherlands" },
+ { "NO", "Norway" },
+ { "NP", "Nepal" },
+ { "NR", "Nauru" },
+ { "NU", "Niue" },
+ { "NZ", "New Zealand" },
+ { "OM", "Oman" },
+ { "PA", "Panama" },
+ { "PE", "Peru" },
+ { "PF", "French Polynesia" },
+ { "PG", "Papua New Guinea" },
+ { "PH", "Philippines" },
+ { "PK", "Pakistan" },
+ { "PL", "Poland" },
+ { "PM", "St. Pierre and Miquelon" },
+ { "PN", "Pitcairn Islands" },
+ { "PR", "Puerto Rico" },
+ { "PS", "Palestine" },
+ { "PT", "Portugal" },
+ { "PW", "Palau" },
+ { "PY", "Paraguay" },
+ { "QA", "Qatar" },
+ { "RE", "Réunion" },
+ { "RO", "Romania" },
+ { "RS", "Serbia" },
+ { "RU", "Russia" },
+ { "RW", "Rwanda" },
+ { "SA", "Saudi Arabia" },
+ { "SB", "Solomon Islands" },
+ { "SC", "Seychelles" },
+ { "SD", "Sudan" },
+ { "SE", "Sweden" },
+ { "SG", "Singapore" },
+ { "SH", "St. Helena, Ascension and Tristan da Cunha" },
+ { "SI", "Slovenia" },
+ { "SJ", "Svalbard and Jan Mayen" },
+ { "SK", "Slovakia" },
+ { "SL", "Sierra Leone" },
+ { "SM", "San Marino" },
+ { "SN", "Senegal" },
+ { "SO", "Somalia" },
+ { "SR", "Suriname" },
+ { "SS", "South Sudan" },
+ { "ST", "Sao Tome and Principe" },
+ { "SV", "El Salvador" },
+ { "SX", "Sint Maarten" },
+ { "SY", "Syria" },
+ { "SZ", "Eswatini" },
+ { "TA", "Tristan da Cunha" }, // Exceptionally reserved.
+ { "TC", "Turks and Caicos Islands" },
+ { "TD", "Chad" },
+ { "TF", "French Southern Territories" },
+ { "TG", "Togo" },
+ { "TH", "Thailand" },
+ { "TJ", "Tajikistan" },
+ { "TK", "Tokelau" },
+ { "TL", "Timor-Leste" },
+ { "TM", "Turkmenistan" },
+ { "TN", "Tunisia" },
+ { "TO", "Tonga" },
+ { "TR", "Turkey" },
+ { "TT", "Trinidad and Tobago" },
+ { "TV", "Tuvalu" },
+ { "TW", "Taiwan" },
+ { "TZ", "Tanzania" },
+ { "UA", "Ukraine" },
+ { "UG", "Uganda" },
+ { "UM", "U.S. Outlying Islands" },
+ { "US", "United States of America" },
+ { "UY", "Uruguay" },
+ { "UZ", "Uzbekistan" },
+ { "VA", "Holy See" },
+ { "VC", "St. Vincent and the Grenadines" },
+ { "VE", "Venezuela" },
+ { "VG", "British Virgin Islands" },
+ { "VI", "U.S. Virgin Islands" },
+ { "VN", "Viet Nam" },
+ { "VU", "Vanuatu" },
+ { "WF", "Wallis and Futuna" },
+ { "WS", "Samoa" },
+ { "XK", "Kosovo" }, // Temporary code, no official ISO code assigned.
+ { "YE", "Yemen" },
+ { "YT", "Mayotte" },
+ { "ZA", "South Africa" },
+ { "ZM", "Zambia" },
+ { "ZW", "Zimbabwe" },
+ { nullptr, nullptr }
+};
+
+// Languages code, language name.
+// Reference:
+// - https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
+// - https://www.localeplanet.com/icu/index.html
+// - https://lh.2xlibre.net/locales/
+
+static const char *language_list[][2] = {
+ { "aa", "Afar" },
+ { "ab", "Abkhazian" },
+ { "ace", "Achinese" },
+ { "ach", "Acoli" },
+ { "ada", "Adangme" },
+ { "ady", "Adyghe" },
+ { "ae", "Avestan" },
+ { "aeb", "Tunisian Arabic" },
+ { "af", "Afrikaans" },
+ { "afh", "Afrihili" },
+ { "agq", "Aghem" },
+ { "ain", "Ainu" },
+ { "agr", "Aguaruna" },
+ { "ak", "Akan" },
+ { "akk", "Akkadian" },
+ { "akz", "Alabama" },
+ { "ale", "Aleut" },
+ { "aln", "Gheg Albanian" },
+ { "alt", "Southern Altai" },
+ { "am", "Amharic" },
+ { "an", "Aragonese" },
+ { "ang", "Old English" },
+ { "anp", "Angika" },
+ { "ar", "Arabic" },
+ { "arc", "Aramaic" },
+ { "arn", "Mapudungun" },
+ { "aro", "Araona" },
+ { "arp", "Arapaho" },
+ { "arq", "Algerian Arabic" },
+ { "ars", "Najdi Arabic" },
+ { "arw", "Arawak" },
+ { "ary", "Moroccan Arabic" },
+ { "arz", "Egyptian Arabic" },
+ { "as", "Assamese" },
+ { "asa", "Asu" },
+ { "ase", "American Sign Language" },
+ { "ast", "Asturian" },
+ { "av", "Avaric" },
+ { "avk", "Kotava" },
+ { "awa", "Awadhi" },
+ { "ayc", "Southern Aymara" },
+ { "ay", "Aymara" },
+ { "az", "Azerbaijani" },
+ { "ba", "Bashkir" },
+ { "bal", "Baluchi" },
+ { "ban", "Balinese" },
+ { "bar", "Bavarian" },
+ { "bas", "Bassa" },
+ { "bax", "Bamun" },
+ { "bbc", "Batak Toba" },
+ { "bbj", "Ghomala" },
+ { "be", "Belarusian" },
+ { "bej", "Beja" },
+ { "bem", "Bemba" },
+ { "ber", "Berber" },
+ { "bew", "Betawi" },
+ { "bez", "Bena" },
+ { "bfd", "Bafut" },
+ { "bfq", "Badaga" },
+ { "bg", "Bulgarian" },
+ { "bhb", "Bhili" },
+ { "bgn", "Western Balochi" },
+ { "bho", "Bhojpuri" },
+ { "bi", "Bislama" },
+ { "bik", "Bikol" },
+ { "bin", "Bini" },
+ { "bjn", "Banjar" },
+ { "bkm", "Kom" },
+ { "bla", "Siksika" },
+ { "bm", "Bambara" },
+ { "bn", "Bengali" },
+ { "bo", "Tibetan" },
+ { "bpy", "Bishnupriya" },
+ { "bqi", "Bakhtiari" },
+ { "br", "Breton" },
+ { "brh", "Brahui" },
+ { "brx", "Bodo" },
+ { "bs", "Bosnian" },
+ { "bss", "Akoose" },
+ { "bua", "Buriat" },
+ { "bug", "Buginese" },
+ { "bum", "Bulu" },
+ { "byn", "Bilin" },
+ { "byv", "Medumba" },
+ { "ca", "Catalan" },
+ { "cad", "Caddo" },
+ { "car", "Carib" },
+ { "cay", "Cayuga" },
+ { "cch", "Atsam" },
+ { "ccp", "Chakma" },
+ { "ce", "Chechen" },
+ { "ceb", "Cebuano" },
+ { "cgg", "Chiga" },
+ { "ch", "Chamorro" },
+ { "chb", "Chibcha" },
+ { "chg", "Chagatai" },
+ { "chk", "Chuukese" },
+ { "chm", "Mari" },
+ { "chn", "Chinook Jargon" },
+ { "cho", "Choctaw" },
+ { "chp", "Chipewyan" },
+ { "chr", "Cherokee" },
+ { "chy", "Cheyenne" },
+ { "cic", "Chickasaw" },
+ { "ckb", "Central Kurdish" },
+ { "csb", "Kashubian" },
+ { "cmn", "Mandarin Chinese" },
+ { "co", "Corsican" },
+ { "cop", "Coptic" },
+ { "cps", "Capiznon" },
+ { "cr", "Cree" },
+ { "crh", "Crimean Tatar" },
+ { "crs", "Seselwa Creole French" },
+ { "cs", "Czech" },
+ { "csb", "Kashubian" },
+ { "cu", "Church Slavic" },
+ { "cv", "Chuvash" },
+ { "cy", "Welsh" },
+ { "da", "Danish" },
+ { "dak", "Dakota" },
+ { "dar", "Dargwa" },
+ { "dav", "Taita" },
+ { "de", "German" },
+ { "del", "Delaware" },
+ { "den", "Slave" },
+ { "dgr", "Dogrib" },
+ { "din", "Dinka" },
+ { "dje", "Zarma" },
+ { "doi", "Dogri" },
+ { "dsb", "Lower Sorbian" },
+ { "dtp", "Central Dusun" },
+ { "dua", "Duala" },
+ { "dum", "Middle Dutch" },
+ { "dv", "Dhivehi" },
+ { "dyo", "Jola-Fonyi" },
+ { "dyu", "Dyula" },
+ { "dz", "Dzongkha" },
+ { "dzg", "Dazaga" },
+ { "ebu", "Embu" },
+ { "ee", "Ewe" },
+ { "efi", "Efik" },
+ { "egl", "Emilian" },
+ { "egy", "Ancient Egyptian" },
+ { "eka", "Ekajuk" },
+ { "el", "Greek" },
+ { "elx", "Elamite" },
+ { "en", "English" },
+ { "enm", "Middle English" },
+ { "eo", "Esperanto" },
+ { "es", "Spanish" },
+ { "esu", "Central Yupik" },
+ { "et", "Estonian" },
+ { "eu", "Basque" },
+ { "ewo", "Ewondo" },
+ { "ext", "Extremaduran" },
+ { "fa", "Persian" },
+ { "fan", "Fang" },
+ { "fat", "Fanti" },
+ { "ff", "Fulah" },
+ { "fi", "Finnish" },
+ { "fil", "Filipino" },
+ { "fit", "Tornedalen Finnish" },
+ { "fj", "Fijian" },
+ { "fo", "Faroese" },
+ { "fon", "Fon" },
+ { "fr", "French" },
+ { "frc", "Cajun French" },
+ { "frm", "Middle French" },
+ { "fro", "Old French" },
+ { "frp", "Arpitan" },
+ { "frr", "Northern Frisian" },
+ { "frs", "Eastern Frisian" },
+ { "fur", "Friulian" },
+ { "fy", "Western Frisian" },
+ { "ga", "Irish" },
+ { "gaa", "Ga" },
+ { "gag", "Gagauz" },
+ { "gan", "Gan Chinese" },
+ { "gay", "Gayo" },
+ { "gba", "Gbaya" },
+ { "gbz", "Zoroastrian Dari" },
+ { "gd", "Scottish Gaelic" },
+ { "gez", "Geez" },
+ { "gil", "Gilbertese" },
+ { "gl", "Galician" },
+ { "glk", "Gilaki" },
+ { "gmh", "Middle High German" },
+ { "gn", "Guarani" },
+ { "goh", "Old High German" },
+ { "gom", "Goan Konkani" },
+ { "gon", "Gondi" },
+ { "gor", "Gorontalo" },
+ { "got", "Gothic" },
+ { "grb", "Grebo" },
+ { "grc", "Ancient Greek" },
+ { "gsw", "Swiss German" },
+ { "gu", "Gujarati" },
+ { "guc", "Wayuu" },
+ { "gur", "Frafra" },
+ { "guz", "Gusii" },
+ { "gv", "Manx" },
+ { "gwi", "Gwichʼin" },
+ { "ha", "Hausa" },
+ { "hai", "Haida" },
+ { "hak", "Hakka Chinese" },
+ { "haw", "Hawaiian" },
+ { "he", "Hebrew" },
+ { "hi", "Hindi" },
+ { "hif", "Fiji Hindi" },
+ { "hil", "Hiligaynon" },
+ { "hit", "Hittite" },
+ { "hmn", "Hmong" },
+ { "ho", "Hiri Motu" },
+ { "hne", "Chhattisgarhi" },
+ { "hr", "Croatian" },
+ { "hsb", "Upper Sorbian" },
+ { "hsn", "Xiang Chinese" },
+ { "ht", "Haitian" },
+ { "hu", "Hungarian" },
+ { "hup", "Hupa" },
+ { "hus", "Huastec" },
+ { "hy", "Armenian" },
+ { "hz", "Herero" },
+ { "ia", "Interlingua" },
+ { "iba", "Iban" },
+ { "ibb", "Ibibio" },
+ { "id", "Indonesian" },
+ { "ie", "Interlingue" },
+ { "ig", "Igbo" },
+ { "ii", "Sichuan Yi" },
+ { "ik", "Inupiaq" },
+ { "ilo", "Iloko" },
+ { "inh", "Ingush" },
+ { "io", "Ido" },
+ { "is", "Icelandic" },
+ { "it", "Italian" },
+ { "iu", "Inuktitut" },
+ { "izh", "Ingrian" },
+ { "ja", "Japanese" },
+ { "jam", "Jamaican Creole English" },
+ { "jbo", "Lojban" },
+ { "jgo", "Ngomba" },
+ { "jmc", "Machame" },
+ { "jpr", "Judeo-Persian" },
+ { "jrb", "Judeo-Arabic" },
+ { "jut", "Jutish" },
+ { "jv", "Javanese" },
+ { "ka", "Georgian" },
+ { "kaa", "Kara-Kalpak" },
+ { "kab", "Kabyle" },
+ { "kac", "Kachin" },
+ { "kaj", "Jju" },
+ { "kam", "Kamba" },
+ { "kaw", "Kawi" },
+ { "kbd", "Kabardian" },
+ { "kbl", "Kanembu" },
+ { "kcg", "Tyap" },
+ { "kde", "Makonde" },
+ { "kea", "Kabuverdianu" },
+ { "ken", "Kenyang" },
+ { "kfo", "Koro" },
+ { "kg", "Kongo" },
+ { "kgp", "Kaingang" },
+ { "kha", "Khasi" },
+ { "kho", "Khotanese" },
+ { "khq", "Koyra Chiini" },
+ { "khw", "Khowar" },
+ { "ki", "Kikuyu" },
+ { "kiu", "Kirmanjki" },
+ { "kj", "Kuanyama" },
+ { "kk", "Kazakh" },
+ { "kkj", "Kako" },
+ { "kl", "Kalaallisut" },
+ { "kln", "Kalenjin" },
+ { "km", "Central Khmer" },
+ { "kmb", "Kimbundu" },
+ { "kn", "Kannada" },
+ { "ko", "Korean" },
+ { "koi", "Komi-Permyak" },
+ { "kok", "Konkani" },
+ { "kos", "Kosraean" },
+ { "kpe", "Kpelle" },
+ { "kr", "Kanuri" },
+ { "krc", "Karachay-Balkar" },
+ { "kri", "Krio" },
+ { "krj", "Kinaray-a" },
+ { "krl", "Karelian" },
+ { "kru", "Kurukh" },
+ { "ks", "Kashmiri" },
+ { "ksb", "Shambala" },
+ { "ksf", "Bafia" },
+ { "ksh", "Colognian" },
+ { "ku", "Kurdish" },
+ { "kum", "Kumyk" },
+ { "kut", "Kutenai" },
+ { "kv", "Komi" },
+ { "kw", "Cornish" },
+ { "ky", "Kirghiz" },
+ { "lag", "Langi" },
+ { "la", "Latin" },
+ { "lad", "Ladino" },
+ { "lag", "Langi" },
+ { "lah", "Lahnda" },
+ { "lam", "Lamba" },
+ { "lb", "Luxembourgish" },
+ { "lez", "Lezghian" },
+ { "lfn", "Lingua Franca Nova" },
+ { "lg", "Ganda" },
+ { "li", "Limburgan" },
+ { "lij", "Ligurian" },
+ { "liv", "Livonian" },
+ { "lkt", "Lakota" },
+ { "lmo", "Lombard" },
+ { "ln", "Lingala" },
+ { "lo", "Lao" },
+ { "lol", "Mongo" },
+ { "lou", "Louisiana Creole" },
+ { "loz", "Lozi" },
+ { "lrc", "Northern Luri" },
+ { "lt", "Lithuanian" },
+ { "ltg", "Latgalian" },
+ { "lu", "Luba-Katanga" },
+ { "lua", "Luba-Lulua" },
+ { "lui", "Luiseno" },
+ { "lun", "Lunda" },
+ { "luo", "Luo" },
+ { "lus", "Mizo" },
+ { "luy", "Luyia" },
+ { "lv", "Latvian" },
+ { "lzh", "Literary Chinese" },
+ { "lzz", "Laz" },
+ { "mad", "Madurese" },
+ { "maf", "Mafa" },
+ { "mag", "Magahi" },
+ { "mai", "Maithili" },
+ { "mak", "Makasar" },
+ { "man", "Mandingo" },
+ { "mas", "Masai" },
+ { "mde", "Maba" },
+ { "mdf", "Moksha" },
+ { "mdr", "Mandar" },
+ { "men", "Mende" },
+ { "mer", "Meru" },
+ { "mfe", "Morisyen" },
+ { "mg", "Malagasy" },
+ { "mga", "Middle Irish" },
+ { "mgh", "Makhuwa-Meetto" },
+ { "mgo", "Metaʼ" },
+ { "mh", "Marshallese" },
+ { "mhr", "Eastern Mari" },
+ { "mi", "Māori" },
+ { "mic", "Mi'kmaq" },
+ { "min", "Minangkabau" },
+ { "miq", "Mískito" },
+ { "mjw", "Karbi" },
+ { "mk", "Macedonian" },
+ { "ml", "Malayalam" },
+ { "mn", "Mongolian" },
+ { "mnc", "Manchu" },
+ { "mni", "Manipuri" },
+ { "mnw", "Mon" },
+ { "mos", "Mossi" },
+ { "moh", "Mohawk" },
+ { "mr", "Marathi" },
+ { "mrj", "Western Mari" },
+ { "ms", "Malay" },
+ { "mt", "Maltese" },
+ { "mua", "Mundang" },
+ { "mus", "Muscogee" },
+ { "mwl", "Mirandese" },
+ { "mwr", "Marwari" },
+ { "mwv", "Mentawai" },
+ { "my", "Burmese" },
+ { "mye", "Myene" },
+ { "myv", "Erzya" },
+ { "mzn", "Mazanderani" },
+ { "na", "Nauru" },
+ { "nah", "Nahuatl" },
+ { "nan", "Min Nan Chinese" },
+ { "nap", "Neapolitan" },
+ { "naq", "Nama" },
+ { "nan", "Min Nan Chinese" },
+ { "nb", "Norwegian Bokmål" },
+ { "nd", "North Ndebele" },
+ { "nds", "Low German" },
+ { "ne", "Nepali" },
+ { "new", "Newari" },
+ { "nhn", "Central Nahuatl" },
+ { "ng", "Ndonga" },
+ { "nia", "Nias" },
+ { "niu", "Niuean" },
+ { "njo", "Ao Naga" },
+ { "nl", "Dutch" },
+ { "nmg", "Kwasio" },
+ { "nn", "Norwegian Nynorsk" },
+ { "nnh", "Ngiemboon" },
+ { "nog", "Nogai" },
+ { "non", "Old Norse" },
+ { "nov", "Novial" },
+ { "nqo", "N'ko" },
+ { "nr", "South Ndebele" },
+ { "nso", "Pedi" },
+ { "nus", "Nuer" },
+ { "nv", "Navajo" },
+ { "nwc", "Classical Newari" },
+ { "ny", "Nyanja" },
+ { "nym", "Nyamwezi" },
+ { "nyn", "Nyankole" },
+ { "nyo", "Nyoro" },
+ { "nzi", "Nzima" },
+ { "oc", "Occitan" },
+ { "oj", "Ojibwa" },
+ { "om", "Oromo" },
+ { "or", "Odia" },
+ { "os", "Ossetic" },
+ { "osa", "Osage" },
+ { "ota", "Ottoman Turkish" },
+ { "pa", "Panjabi" },
+ { "pag", "Pangasinan" },
+ { "pal", "Pahlavi" },
+ { "pam", "Pampanga" },
+ { "pap", "Papiamento" },
+ { "pau", "Palauan" },
+ { "pcd", "Picard" },
+ { "pcm", "Nigerian Pidgin" },
+ { "pdc", "Pennsylvania German" },
+ { "pdt", "Plautdietsch" },
+ { "peo", "Old Persian" },
+ { "pfl", "Palatine German" },
+ { "phn", "Phoenician" },
+ { "pi", "Pali" },
+ { "pl", "Polish" },
+ { "pms", "Piedmontese" },
+ { "pnt", "Pontic" },
+ { "pon", "Pohnpeian" },
+ { "pr", "Pirate" },
+ { "prg", "Prussian" },
+ { "pro", "Old Provençal" },
+ { "prs", "Dari" },
+ { "ps", "Pushto" },
+ { "pt", "Portuguese" },
+ { "qu", "Quechua" },
+ { "quc", "K'iche" },
+ { "qug", "Chimborazo Highland Quichua" },
+ { "quy", "Ayacucho Quechua" },
+ { "quz", "Cusco Quechua" },
+ { "raj", "Rajasthani" },
+ { "rap", "Rapanui" },
+ { "rar", "Rarotongan" },
+ { "rgn", "Romagnol" },
+ { "rif", "Riffian" },
+ { "rm", "Romansh" },
+ { "rn", "Rundi" },
+ { "ro", "Romanian" },
+ { "rof", "Rombo" },
+ { "rom", "Romany" },
+ { "rtm", "Rotuman" },
+ { "ru", "Russian" },
+ { "rue", "Rusyn" },
+ { "rug", "Roviana" },
+ { "rup", "Aromanian" },
+ { "rw", "Kinyarwanda" },
+ { "rwk", "Rwa" },
+ { "sa", "Sanskrit" },
+ { "sad", "Sandawe" },
+ { "sah", "Sakha" },
+ { "sam", "Samaritan Aramaic" },
+ { "saq", "Samburu" },
+ { "sas", "Sasak" },
+ { "sat", "Santali" },
+ { "saz", "Saurashtra" },
+ { "sba", "Ngambay" },
+ { "sbp", "Sangu" },
+ { "sc", "Sardinian" },
+ { "scn", "Sicilian" },
+ { "sco", "Scots" },
+ { "sd", "Sindhi" },
+ { "sdc", "Sassarese Sardinian" },
+ { "sdh", "Southern Kurdish" },
+ { "se", "Northern Sami" },
+ { "see", "Seneca" },
+ { "seh", "Sena" },
+ { "sei", "Seri" },
+ { "sel", "Selkup" },
+ { "ses", "Koyraboro Senni" },
+ { "sg", "Sango" },
+ { "sga", "Old Irish" },
+ { "sgs", "Samogitian" },
+ { "sh", "Serbo-Croatian" },
+ { "shi", "Tachelhit" },
+ { "shn", "Shan" },
+ { "shs", "Shuswap" },
+ { "shu", "Chadian Arabic" },
+ { "si", "Sinhala" },
+ { "sid", "Sidamo" },
+ { "sk", "Slovak" },
+ { "sl", "Slovenian" },
+ { "sli", "Lower Silesian" },
+ { "sly", "Selayar" },
+ { "sm", "Samoan" },
+ { "sma", "Southern Sami" },
+ { "smj", "Lule Sami" },
+ { "smn", "Inari Sami" },
+ { "sms", "Skolt Sami" },
+ { "sn", "Shona" },
+ { "snk", "Soninke" },
+ { "so", "Somali" },
+ { "sog", "Sogdien" },
+ { "son", "Songhai" },
+ { "sq", "Albanian" },
+ { "sr", "Serbian" },
+ { "srn", "Sranan Tongo" },
+ { "srr", "Serer" },
+ { "ss", "Swati" },
+ { "ssy", "Saho" },
+ { "st", "Southern Sotho" },
+ { "stq", "Saterland Frisian" },
+ { "su", "Sundanese" },
+ { "suk", "Sukuma" },
+ { "sus", "Susu" },
+ { "sux", "Sumerian" },
+ { "sv", "Swedish" },
+ { "sw", "Swahili" },
+ { "swb", "Comorian" },
+ { "swc", "Congo Swahili" },
+ { "syc", "Classical Syriac" },
+ { "syr", "Syriac" },
+ { "szl", "Silesian" },
+ { "ta", "Tamil" },
+ { "tcy", "Tulu" },
+ { "te", "Telugu" },
+ { "tem", "Timne" },
+ { "teo", "Teso" },
+ { "ter", "Tereno" },
+ { "tet", "Tetum" },
+ { "tg", "Tajik" },
+ { "th", "Thai" },
+ { "the", "Chitwania Tharu" },
+ { "ti", "Tigrinya" },
+ { "tig", "Tigre" },
+ { "tiv", "Tiv" },
+ { "tk", "Turkmen" },
+ { "tkl", "Tokelau" },
+ { "tkr", "Tsakhur" },
+ { "tl", "Tagalog" },
+ { "tlh", "Klingon" },
+ { "tli", "Tlingit" },
+ { "tly", "Talysh" },
+ { "tmh", "Tamashek" },
+ { "tn", "Tswana" },
+ { "to", "Tongan" },
+ { "tog", "Nyasa Tonga" },
+ { "tpi", "Tok Pisin" },
+ { "tr", "Turkish" },
+ { "tru", "Turoyo" },
+ { "trv", "Taroko" },
+ { "ts", "Tsonga" },
+ { "tsd", "Tsakonian" },
+ { "tsi", "Tsimshian" },
+ { "tt", "Tatar" },
+ { "ttt", "Muslim Tat" },
+ { "tum", "Tumbuka" },
+ { "tvl", "Tuvalu" },
+ { "tw", "Twi" },
+ { "twq", "Tasawaq" },
+ { "ty", "Tahitian" },
+ { "tyv", "Tuvinian" },
+ { "tzm", "Central Atlas Tamazight" },
+ { "udm", "Udmurt" },
+ { "ug", "Uyghur" },
+ { "uga", "Ugaritic" },
+ { "uk", "Ukrainian" },
+ { "umb", "Umbundu" },
+ { "unm", "Unami" },
+ { "ur", "Urdu" },
+ { "uz", "Uzbek" },
+ { "vai", "Vai" },
+ { "ve", "Venda" },
+ { "vec", "Venetian" },
+ { "vep", "Veps" },
+ { "vi", "Vietnamese" },
+ { "vls", "West Flemish" },
+ { "vmf", "Main-Franconian" },
+ { "vo", "Volapük" },
+ { "vot", "Votic" },
+ { "vro", "Võro" },
+ { "vun", "Vunjo" },
+ { "wa", "Walloon" },
+ { "wae", "Walser" },
+ { "wal", "Wolaytta" },
+ { "war", "Waray" },
+ { "was", "Washo" },
+ { "wbp", "Warlpiri" },
+ { "wo", "Wolof" },
+ { "wuu", "Wu Chinese" },
+ { "xal", "Kalmyk" },
+ { "xh", "Xhosa" },
+ { "xmf", "Mingrelian" },
+ { "xog", "Soga" },
+ { "yao", "Yao" },
+ { "yap", "Yapese" },
+ { "yav", "Yangben" },
+ { "ybb", "Yemba" },
+ { "yi", "Yiddish" },
+ { "yo", "Yoruba" },
+ { "yrl", "Nheengatu" },
+ { "yue", "Yue Chinese" },
+ { "yuw", "Papua New Guinea" },
+ { "za", "Zhuang" },
+ { "zap", "Zapotec" },
+ { "zbl", "Blissymbols" },
+ { "zea", "Zeelandic" },
+ { "zen", "Zenaga" },
+ { "zgh", "Standard Moroccan Tamazight" },
+ { "zh", "Chinese" },
+ { "zu", "Zulu" },
+ { "zun", "Zuni" },
+ { "zza", "Zaza" },
+ { nullptr, nullptr }
+};
+
+// Additional regional variants.
+// Variant name, supported languages.
+
+static const char *locale_variants[][2] = {
+ { "valencia", "ca" },
+ { "iqtelif", "tt" },
+ { "saaho", "aa" },
+ { "tradnl", "es" },
+ { nullptr, nullptr },
+};
+
+// Script names and codes (excludes typographic variants, special codes, reserved codes and aliases for combined scripts).
+// Reference:
+// - https://en.wikipedia.org/wiki/ISO_15924
+
+static const char *script_list[][2] = {
+ { "Adlam", "Adlm" },
+ { "Afaka", "Afak" },
+ { "Caucasian Albanian", "Aghb" },
+ { "Ahom", "Ahom" },
+ { "Arabic", "Arab" },
+ { "Imperial Aramaic", "Armi" },
+ { "Armenian", "Armn" },
+ { "Avestan", "Avst" },
+ { "Balinese", "Bali" },
+ { "Bamum", "Bamu" },
+ { "Bassa Vah", "Bass" },
+ { "Batak", "Batk" },
+ { "Bengali", "Beng" },
+ { "Bhaiksuki", "Bhks" },
+ { "Blissymbols", "Blis" },
+ { "Bopomofo", "Bopo" },
+ { "Brahmi", "Brah" },
+ { "Braille", "Brai" },
+ { "Buginese", "Bugi" },
+ { "Buhid", "Buhd" },
+ { "Chakma", "Cakm" },
+ { "Unified Canadian Aboriginal", "Cans" },
+ { "Carian", "Cari" },
+ { "Cham", "Cham" },
+ { "Cherokee", "Cher" },
+ { "Chorasmian", "Chrs" },
+ { "Cirth", "Cirt" },
+ { "Coptic", "Copt" },
+ { "Cypro-Minoan", "Cpmn" },
+ { "Cypriot", "Cprt" },
+ { "Cyrillic", "Cyrl" },
+ { "Devanagari", "Deva" },
+ { "Dives Akuru", "Diak" },
+ { "Dogra", "Dogr" },
+ { "Deseret", "Dsrt" },
+ { "Duployan", "Dupl" },
+ { "Egyptian demotic", "Egyd" },
+ { "Egyptian hieratic", "Egyh" },
+ { "Egyptian hieroglyphs", "Egyp" },
+ { "Elbasan", "Elba" },
+ { "Elymaic", "Elym" },
+ { "Ethiopic", "Ethi" },
+ { "Khutsuri", "Geok" },
+ { "Georgian", "Geor" },
+ { "Glagolitic", "Glag" },
+ { "Gunjala Gondi", "Gong" },
+ { "Masaram Gondi", "Gonm" },
+ { "Gothic", "Goth" },
+ { "Grantha", "Gran" },
+ { "Greek", "Grek" },
+ { "Gujarati", "Gujr" },
+ { "Gurmukhi", "Guru" },
+ { "Hangul", "Hang" },
+ { "Han", "Hani" },
+ { "Hanunoo", "Hano" },
+ { "Simplified", "Hans" },
+ { "Traditional", "Hant" },
+ { "Hatran", "Hatr" },
+ { "Hebrew", "Hebr" },
+ { "Hiragana", "Hira" },
+ { "Anatolian Hieroglyphs", "Hluw" },
+ { "Pahawh Hmong", "Hmng" },
+ { "Nyiakeng Puachue Hmong", "Hmnp" },
+ { "Old Hungarian", "Hung" },
+ { "Indus", "Inds" },
+ { "Old Italic", "Ital" },
+ { "Javanese", "Java" },
+ { "Jurchen", "Jurc" },
+ { "Kayah Li", "Kali" },
+ { "Katakana", "Kana" },
+ { "Kharoshthi", "Khar" },
+ { "Khmer", "Khmr" },
+ { "Khojki", "Khoj" },
+ { "Khitan large script", "Kitl" },
+ { "Khitan small script", "Kits" },
+ { "Kannada", "Knda" },
+ { "Kpelle", "Kpel" },
+ { "Kaithi", "Kthi" },
+ { "Tai Tham", "Lana" },
+ { "Lao", "Laoo" },
+ { "Latin", "Latn" },
+ { "Leke", "Leke" },
+ { "Lepcha", "Lepc" },
+ { "Limbu", "Limb" },
+ { "Linear A", "Lina" },
+ { "Linear B", "Linb" },
+ { "Lisu", "Lisu" },
+ { "Loma", "Loma" },
+ { "Lycian", "Lyci" },
+ { "Lydian", "Lydi" },
+ { "Mahajani", "Mahj" },
+ { "Makasar", "Maka" },
+ { "Mandaic", "Mand" },
+ { "Manichaean", "Mani" },
+ { "Marchen", "Marc" },
+ { "Mayan Hieroglyphs", "Maya" },
+ { "Medefaidrin", "Medf" },
+ { "Mende Kikakui", "Mend" },
+ { "Meroitic Cursive", "Merc" },
+ { "Meroitic Hieroglyphs", "Mero" },
+ { "Malayalam", "Mlym" },
+ { "Modi", "Modi" },
+ { "Mongolian", "Mong" },
+ { "Moon", "Moon" },
+ { "Mro", "Mroo" },
+ { "Meitei Mayek", "Mtei" },
+ { "Multani", "Mult" },
+ { "Myanmar (Burmese)", "Mymr" },
+ { "Nandinagari", "Nand" },
+ { "Old North Arabian", "Narb" },
+ { "Nabataean", "Nbat" },
+ { "Newa", "Newa" },
+ { "Naxi Dongba", "Nkdb" },
+ { "Nakhi Geba", "Nkgb" },
+ { "N'ko", "Nkoo" },
+ { "Nüshu", "Nshu" },
+ { "Ogham", "Ogam" },
+ { "Ol Chiki", "Olck" },
+ { "Old Turkic", "Orkh" },
+ { "Oriya", "Orya" },
+ { "Osage", "Osge" },
+ { "Osmanya", "Osma" },
+ { "Old Uyghur", "Ougr" },
+ { "Palmyrene", "Palm" },
+ { "Pau Cin Hau", "Pauc" },
+ { "Proto-Cuneiform", "Pcun" },
+ { "Proto-Elamite", "Pelm" },
+ { "Old Permic", "Perm" },
+ { "Phags-pa", "Phag" },
+ { "Inscriptional Pahlavi", "Phli" },
+ { "Psalter Pahlavi", "Phlp" },
+ { "Book Pahlavi", "Phlv" },
+ { "Phoenician", "Phnx" },
+ { "Klingon", "Piqd" },
+ { "Miao", "Plrd" },
+ { "Inscriptional Parthian", "Prti" },
+ { "Proto-Sinaitic", "Psin" },
+ { "Ranjana", "Ranj" },
+ { "Rejang", "Rjng" },
+ { "Hanifi Rohingya", "Rohg" },
+ { "Rongorongo", "Roro" },
+ { "Runic", "Runr" },
+ { "Samaritan", "Samr" },
+ { "Sarati", "Sara" },
+ { "Old South Arabian", "Sarb" },
+ { "Saurashtra", "Saur" },
+ { "SignWriting", "Sgnw" },
+ { "Shavian", "Shaw" },
+ { "Sharada", "Shrd" },
+ { "Shuishu", "Shui" },
+ { "Siddham", "Sidd" },
+ { "Khudawadi", "Sind" },
+ { "Sinhala", "Sinh" },
+ { "Sogdian", "Sogd" },
+ { "Old Sogdian", "Sogo" },
+ { "Sora Sompeng", "Sora" },
+ { "Soyombo", "Soyo" },
+ { "Sundanese", "Sund" },
+ { "Syloti Nagri", "Sylo" },
+ { "Syriac", "Syrc" },
+ { "Tagbanwa", "Tagb" },
+ { "Takri", "Takr" },
+ { "Tai Le", "Tale" },
+ { "New Tai Lue", "Talu" },
+ { "Tamil", "Taml" },
+ { "Tangut", "Tang" },
+ { "Tai Viet", "Tavt" },
+ { "Telugu", "Telu" },
+ { "Tengwar", "Teng" },
+ { "Tifinagh", "Tfng" },
+ { "Tagalog", "Tglg" },
+ { "Thaana", "Thaa" },
+ { "Thai", "Thai" },
+ { "Tibetan", "Tibt" },
+ { "Tirhuta", "Tirh" },
+ { "Tangsa", "Tnsa" },
+ { "Toto", "Toto" },
+ { "Ugaritic", "Ugar" },
+ { "Vai", "Vaii" },
+ { "Visible Speech", "Visp" },
+ { "Vithkuqi", "Vith" },
+ { "Warang Citi", "Wara" },
+ { "Wancho", "Wcho" },
+ { "Woleai", "Wole" },
+ { "Old Persian", "Xpeo" },
+ { "Cuneiform", "Xsux" },
+ { "Yezidi", "Yezi" },
+ { "Yi", "Yiii" },
+ { "Zanabazar Square", "Zanb" },
+ { nullptr, nullptr }
+};
+
+#endif // LOCALES_H
diff --git a/core/string/node_path.cpp b/core/string/node_path.cpp
index 7ab85ac9d0..238897c2b1 100644
--- a/core/string/node_path.cpp
+++ b/core/string/node_path.cpp
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -368,7 +368,7 @@ NodePath::NodePath(const String &p_path) {
for (int i = from; i <= path.length(); i++) {
if (path[i] == ':' || path[i] == 0) {
String str = path.substr(from, i - from);
- if (str == "") {
+ if (str.is_empty()) {
if (path[i] == 0) {
continue; // Allow end-of-path :
}
diff --git a/core/string/node_path.h b/core/string/node_path.h
index a277ab26fa..53976bd524 100644
--- a/core/string/node_path.h
+++ b/core/string/node_path.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/optimized_translation.cpp b/core/string/optimized_translation.cpp
index f8be564740..07b58f2418 100644
--- a/core/string/optimized_translation.cpp
+++ b/core/string/optimized_translation.cpp
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/optimized_translation.h b/core/string/optimized_translation.h
index bccf932383..f3dbfe8f5c 100644
--- a/core/string/optimized_translation.h
+++ b/core/string/optimized_translation.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -38,7 +38,7 @@ class OptimizedTranslation : public Translation {
//this translation uses a sort of modified perfect hash algorithm
//it requires hashing strings twice and then does a binary search,
- //so it's slower, but at the same time it has an extreemly high chance
+ //so it's slower, but at the same time it has an extremely high chance
//of catching untranslated strings
//load/store friendly types
diff --git a/core/string/print_string.cpp b/core/string/print_string.cpp
index adc218f597..97e119bcf6 100644
--- a/core/string/print_string.cpp
+++ b/core/string/print_string.cpp
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/print_string.h b/core/string/print_string.h
index 3cd170b68e..669d2ea316 100644
--- a/core/string/print_string.h
+++ b/core/string/print_string.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/string_buffer.h b/core/string/string_buffer.h
index 33897c3674..424952f786 100644
--- a/core/string/string_buffer.h
+++ b/core/string/string_buffer.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/string_builder.cpp b/core/string/string_builder.cpp
index 834c87c845..7359ff59e1 100644
--- a/core/string/string_builder.cpp
+++ b/core/string/string_builder.cpp
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -33,7 +33,7 @@
#include <string.h>
StringBuilder &StringBuilder::append(const String &p_string) {
- if (p_string == String()) {
+ if (p_string.is_empty()) {
return *this;
}
diff --git a/core/string/string_builder.h b/core/string/string_builder.h
index 30ce2a06f7..897efa95ef 100644
--- a/core/string/string_builder.h
+++ b/core/string/string_builder.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/string_name.cpp b/core/string/string_name.cpp
index 9024f60dae..2e941b8037 100644
--- a/core/string/string_name.cpp
+++ b/core/string/string_name.cpp
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -73,23 +73,38 @@ void StringName::cleanup() {
d = d->next;
}
}
- print_line("\nStringName Reference Ranking:\n");
+
+ print_line("\nStringName reference ranking (from most to least referenced):\n");
+
data.sort_custom<DebugSortReferences>();
- for (int i = 0; i < MIN(100, data.size()); i++) {
+ int unreferenced_stringnames = 0;
+ int rarely_referenced_stringnames = 0;
+ for (int i = 0; i < data.size(); i++) {
print_line(itos(i + 1) + ": " + data[i]->get_name() + " - " + itos(data[i]->debug_references));
+ if (data[i]->debug_references == 0) {
+ unreferenced_stringnames += 1;
+ } else if (data[i]->debug_references < 5) {
+ rarely_referenced_stringnames += 1;
+ }
}
+
+ print_line(vformat("\nOut of %d StringNames, %d StringNames were never referenced during this run (0 times) (%.2f%%).", data.size(), unreferenced_stringnames, unreferenced_stringnames / float(data.size()) * 100));
+ print_line(vformat("Out of %d StringNames, %d StringNames were rarely referenced during this run (1-4 times) (%.2f%%).", data.size(), rarely_referenced_stringnames, rarely_referenced_stringnames / float(data.size()) * 100));
}
#endif
int lost_strings = 0;
for (int i = 0; i < STRING_TABLE_LEN; i++) {
while (_table[i]) {
_Data *d = _table[i];
- lost_strings++;
- if (d->static_count.get() != d->refcount.get() && OS::get_singleton()->is_stdout_verbose()) {
- if (d->cname) {
- print_line("Orphan StringName: " + String(d->cname));
- } else {
- print_line("Orphan StringName: " + String(d->name));
+ if (d->static_count.get() != d->refcount.get()) {
+ lost_strings++;
+
+ if (OS::get_singleton()->is_stdout_verbose()) {
+ if (d->cname) {
+ print_line("Orphan StringName: " + String(d->cname));
+ } else {
+ print_line("Orphan StringName: " + String(d->name));
+ }
}
}
@@ -310,7 +325,7 @@ StringName::StringName(const String &p_name, bool p_static) {
ERR_FAIL_COND(!configured);
- if (p_name == String()) {
+ if (p_name.is_empty()) {
return;
}
@@ -434,7 +449,7 @@ StringName StringName::search(const char32_t *p_name) {
}
StringName StringName::search(const String &p_name) {
- ERR_FAIL_COND_V(p_name == "", StringName());
+ ERR_FAIL_COND_V(p_name.is_empty(), StringName());
MutexLock lock(mutex);
diff --git a/core/string/string_name.h b/core/string/string_name.h
index ce7988744b..6f08d32981 100644
--- a/core/string/string_name.h
+++ b/core/string/string_name.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -181,6 +181,18 @@ bool operator!=(const char *p_name, const StringName &p_string_name);
StringName _scs_create(const char *p_chr, bool p_static = false);
+/*
+ * The SNAME macro is used to speed up StringName creation, as it allows caching it after the first usage in a very efficient way.
+ * It should NOT be used everywhere, but instead in places where high performance is required and the creation of a StringName
+ * can be costly. Places where it should be used are:
+ * - Control::get_theme_*(<name> and Window::get_theme_*(<name> functions.
+ * - emit_signal(<name>,..) function
+ * - call_deferred(<name>,..) function
+ * - Comparisons to a StringName in overridden _set and _get methods.
+ *
+ * Use in places that can be called hundreds of times per frame (or more) is recommended, but this situation is very rare. If in doubt, do not use.
+ */
+
#define SNAME(m_arg) ([]() -> const StringName & { static StringName sname = _scs_create(m_arg, true); return sname; })()
#endif // STRING_NAME_H
diff --git a/core/string/translation.cpp b/core/string/translation.cpp
index b98aad9b58..c41828de05 100644
--- a/core/string/translation.cpp
+++ b/core/string/translation.cpp
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -33,793 +33,12 @@
#include "core/config/project_settings.h"
#include "core/io/resource_loader.h"
#include "core/os/os.h"
+#include "core/string/locales.h"
#ifdef TOOLS_ENABLED
#include "main/main.h"
#endif
-// ISO 639-1 language codes (and a couple of three-letter ISO 639-2 codes),
-// with the addition of glibc locales with their regional identifiers.
-// This list must match the language names (in English) of locale_names.
-//
-// References:
-// - https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
-// - https://lh.2xlibre.net/locales/
-// - https://iso639-3.sil.org/
-
-static const char *locale_list[] = {
- "aa", // Afar
- "aa_DJ", // Afar (Djibouti)
- "aa_ER", // Afar (Eritrea)
- "aa_ET", // Afar (Ethiopia)
- "af", // Afrikaans
- "af_ZA", // Afrikaans (South Africa)
- "agr_PE", // Aguaruna (Peru)
- "ak_GH", // Akan (Ghana)
- "am_ET", // Amharic (Ethiopia)
- "an_ES", // Aragonese (Spain)
- "anp_IN", // Angika (India)
- "ar", // Arabic
- "ar_AE", // Arabic (United Arab Emirates)
- "ar_BH", // Arabic (Bahrain)
- "ar_DZ", // Arabic (Algeria)
- "ar_EG", // Arabic (Egypt)
- "ar_IN", // Arabic (India)
- "ar_IQ", // Arabic (Iraq)
- "ar_JO", // Arabic (Jordan)
- "ar_KW", // Arabic (Kuwait)
- "ar_LB", // Arabic (Lebanon)
- "ar_LY", // Arabic (Libya)
- "ar_MA", // Arabic (Morocco)
- "ar_OM", // Arabic (Oman)
- "ar_QA", // Arabic (Qatar)
- "ar_SA", // Arabic (Saudi Arabia)
- "ar_SD", // Arabic (Sudan)
- "ar_SS", // Arabic (South Soudan)
- "ar_SY", // Arabic (Syria)
- "ar_TN", // Arabic (Tunisia)
- "ar_YE", // Arabic (Yemen)
- "as_IN", // Assamese (India)
- "ast_ES", // Asturian (Spain)
- "ayc_PE", // Southern Aymara (Peru)
- "ay_PE", // Aymara (Peru)
- "az", // Azerbaijani
- "az_AZ", // Azerbaijani (Azerbaijan)
- "be", // Belarusian
- "be_BY", // Belarusian (Belarus)
- "bem_ZM", // Bemba (Zambia)
- "ber_DZ", // Berber languages (Algeria)
- "ber_MA", // Berber languages (Morocco)
- "bg", // Bulgarian
- "bg_BG", // Bulgarian (Bulgaria)
- "bhb_IN", // Bhili (India)
- "bho_IN", // Bhojpuri (India)
- "bi_TV", // Bislama (Tuvalu)
- "bn", // Bengali
- "bn_BD", // Bengali (Bangladesh)
- "bn_IN", // Bengali (India)
- "bo", // Tibetan
- "bo_CN", // Tibetan (China)
- "bo_IN", // Tibetan (India)
- "br", // Breton
- "br_FR", // Breton (France)
- "brx_IN", // Bodo (India)
- "bs_BA", // Bosnian (Bosnia and Herzegovina)
- "byn_ER", // Bilin (Eritrea)
- "ca", // Catalan
- "ca_AD", // Catalan (Andorra)
- "ca_ES", // Catalan (Spain)
- "ca_FR", // Catalan (France)
- "ca_IT", // Catalan (Italy)
- "ce_RU", // Chechen (Russia)
- "chr_US", // Cherokee (United States)
- "cmn_TW", // Mandarin Chinese (Taiwan)
- "crh_UA", // Crimean Tatar (Ukraine)
- "csb_PL", // Kashubian (Poland)
- "cs", // Czech
- "cs_CZ", // Czech (Czech Republic)
- "cv_RU", // Chuvash (Russia)
- "cy_GB", // Welsh (United Kingdom)
- "da", // Danish
- "da_DK", // Danish (Denmark)
- "de", // German
- "de_AT", // German (Austria)
- "de_BE", // German (Belgium)
- "de_CH", // German (Switzerland)
- "de_DE", // German (Germany)
- "de_IT", // German (Italy)
- "de_LU", // German (Luxembourg)
- "doi_IN", // Dogri (India)
- "dv_MV", // Dhivehi (Maldives)
- "dz_BT", // Dzongkha (Bhutan)
- "el", // Greek
- "el_CY", // Greek (Cyprus)
- "el_GR", // Greek (Greece)
- "en", // English
- "en_AG", // English (Antigua and Barbuda)
- "en_AU", // English (Australia)
- "en_BW", // English (Botswana)
- "en_CA", // English (Canada)
- "en_DK", // English (Denmark)
- "en_GB", // English (United Kingdom)
- "en_HK", // English (Hong Kong)
- "en_IE", // English (Ireland)
- "en_IL", // English (Israel)
- "en_IN", // English (India)
- "en_NG", // English (Nigeria)
- "en_NZ", // English (New Zealand)
- "en_PH", // English (Philippines)
- "en_SG", // English (Singapore)
- "en_US", // English (United States)
- "en_ZA", // English (South Africa)
- "en_ZM", // English (Zambia)
- "en_ZW", // English (Zimbabwe)
- "eo", // Esperanto
- "es", // Spanish
- "es_AR", // Spanish (Argentina)
- "es_BO", // Spanish (Bolivia)
- "es_CL", // Spanish (Chile)
- "es_CO", // Spanish (Colombia)
- "es_CR", // Spanish (Costa Rica)
- "es_CU", // Spanish (Cuba)
- "es_DO", // Spanish (Dominican Republic)
- "es_EC", // Spanish (Ecuador)
- "es_ES", // Spanish (Spain)
- "es_GT", // Spanish (Guatemala)
- "es_HN", // Spanish (Honduras)
- "es_MX", // Spanish (Mexico)
- "es_NI", // Spanish (Nicaragua)
- "es_PA", // Spanish (Panama)
- "es_PE", // Spanish (Peru)
- "es_PR", // Spanish (Puerto Rico)
- "es_PY", // Spanish (Paraguay)
- "es_SV", // Spanish (El Salvador)
- "es_US", // Spanish (United States)
- "es_UY", // Spanish (Uruguay)
- "es_VE", // Spanish (Venezuela)
- "et", // Estonian
- "et_EE", // Estonian (Estonia)
- "eu", // Basque
- "eu_ES", // Basque (Spain)
- "fa", // Persian
- "fa_IR", // Persian (Iran)
- "ff_SN", // Fulah (Senegal)
- "fi", // Finnish
- "fi_FI", // Finnish (Finland)
- "fil", // Filipino
- "fil_PH", // Filipino (Philippines)
- "fo_FO", // Faroese (Faroe Islands)
- "fr", // French
- "fr_BE", // French (Belgium)
- "fr_CA", // French (Canada)
- "fr_CH", // French (Switzerland)
- "fr_FR", // French (France)
- "fr_LU", // French (Luxembourg)
- "fur_IT", // Friulian (Italy)
- "fy_DE", // Western Frisian (Germany)
- "fy_NL", // Western Frisian (Netherlands)
- "ga", // Irish
- "ga_IE", // Irish (Ireland)
- "gd_GB", // Scottish Gaelic (United Kingdom)
- "gez_ER", // Geez (Eritrea)
- "gez_ET", // Geez (Ethiopia)
- "gl", // Galician
- "gl_ES", // Galician (Spain)
- "gu_IN", // Gujarati (India)
- "gv_GB", // Manx (United Kingdom)
- "hak_TW", // Hakka Chinese (Taiwan)
- "ha_NG", // Hausa (Nigeria)
- "he", // Hebrew
- "he_IL", // Hebrew (Israel)
- "hi", // Hindi
- "hi_IN", // Hindi (India)
- "hne_IN", // Chhattisgarhi (India)
- "hr", // Croatian
- "hr_HR", // Croatian (Croatia)
- "hsb_DE", // Upper Sorbian (Germany)
- "ht_HT", // Haitian (Haiti)
- "hu", // Hungarian
- "hu_HU", // Hungarian (Hungary)
- "hus_MX", // Huastec (Mexico)
- "hy_AM", // Armenian (Armenia)
- "ia_FR", // Interlingua (France)
- "id", // Indonesian
- "id_ID", // Indonesian (Indonesia)
- "ig_NG", // Igbo (Nigeria)
- "ik_CA", // Inupiaq (Canada)
- "is", // Icelandic
- "is_IS", // Icelandic (Iceland)
- "it", // Italian
- "it_CH", // Italian (Switzerland)
- "it_IT", // Italian (Italy)
- "iu_CA", // Inuktitut (Canada)
- "ja", // Japanese
- "ja_JP", // Japanese (Japan)
- "kab_DZ", // Kabyle (Algeria)
- "ka", // Georgian
- "ka_GE", // Georgian (Georgia)
- "kk_KZ", // Kazakh (Kazakhstan)
- "kl_GL", // Kalaallisut (Greenland)
- "km", // Central Khmer
- "km_KH", // Central Khmer (Cambodia)
- "kn_IN", // Kannada (India)
- "kok_IN", // Konkani (India)
- "ko", // Korean
- "ko_KR", // Korean (South Korea)
- "ks_IN", // Kashmiri (India)
- "ku", // Kurdish
- "ku_TR", // Kurdish (Turkey)
- "kw_GB", // Cornish (United Kingdom)
- "ky_KG", // Kirghiz (Kyrgyzstan)
- "lb_LU", // Luxembourgish (Luxembourg)
- "lg_UG", // Ganda (Uganda)
- "li_BE", // Limburgan (Belgium)
- "li_NL", // Limburgan (Netherlands)
- "lij_IT", // Ligurian (Italy)
- "ln_CD", // Lingala (Congo)
- "lo_LA", // Lao (Laos)
- "lt", // Lithuanian
- "lt_LT", // Lithuanian (Lithuania)
- "lv", // Latvian
- "lv_LV", // Latvian (Latvia)
- "lzh_TW", // Literary Chinese (Taiwan)
- "mag_IN", // Magahi (India)
- "mai_IN", // Maithili (India)
- "mg_MG", // Malagasy (Madagascar)
- "mh_MH", // Marshallese (Marshall Islands)
- "mhr_RU", // Eastern Mari (Russia)
- "mi", // Māori
- "mi_NZ", // Māori (New Zealand)
- "miq_NI", // Mískito (Nicaragua)
- "mk", // Macedonian
- "mk_MK", // Macedonian (Macedonia)
- "ml", // Malayalam
- "ml_IN", // Malayalam (India)
- "mni_IN", // Manipuri (India)
- "mn_MN", // Mongolian (Mongolia)
- "mr", // Marathi
- "mr_IN", // Marathi (India)
- "ms", // Malay
- "ms_MY", // Malay (Malaysia)
- "mt", // Maltese
- "mt_MT", // Maltese (Malta)
- "my_MM", // Burmese (Myanmar)
- "myv_RU", // Erzya (Russia)
- "nah_MX", // Nahuatl languages (Mexico)
- "nan_TW", // Min Nan Chinese (Taiwan)
- "nb", // Norwegian Bokmål
- "nb_NO", // Norwegian Bokmål (Norway)
- "nds_DE", // Low German (Germany)
- "nds_NL", // Low German (Netherlands)
- "ne_NP", // Nepali (Nepal)
- "nhn_MX", // Central Nahuatl (Mexico)
- "niu_NU", // Niuean (Niue)
- "niu_NZ", // Niuean (New Zealand)
- "nl", // Dutch
- "nl_AW", // Dutch (Aruba)
- "nl_BE", // Dutch (Belgium)
- "nl_NL", // Dutch (Netherlands)
- "nn", // Norwegian Nynorsk
- "nn_NO", // Norwegian Nynorsk (Norway)
- "nr_ZA", // South Ndebele (South Africa)
- "nso_ZA", // Pedi (South Africa)
- "oc_FR", // Occitan (France)
- "om", // Oromo
- "om_ET", // Oromo (Ethiopia)
- "om_KE", // Oromo (Kenya)
- "or", // Oriya
- "or_IN", // Oriya (India)
- "os_RU", // Ossetian (Russia)
- "pa_IN", // Panjabi (India)
- "pap", // Papiamento
- "pap_AN", // Papiamento (Netherlands Antilles)
- "pap_AW", // Papiamento (Aruba)
- "pap_CW", // Papiamento (Curaçao)
- "pa_PK", // Panjabi (Pakistan)
- "pl", // Polish
- "pl_PL", // Polish (Poland)
- "pr", // Pirate
- "ps_AF", // Pushto (Afghanistan)
- "pt", // Portuguese
- "pt_BR", // Portuguese (Brazil)
- "pt_PT", // Portuguese (Portugal)
- "quy_PE", // Ayacucho Quechua (Peru)
- "quz_PE", // Cusco Quechua (Peru)
- "raj_IN", // Rajasthani (India)
- "ro", // Romanian
- "ro_RO", // Romanian (Romania)
- "ru", // Russian
- "ru_RU", // Russian (Russia)
- "ru_UA", // Russian (Ukraine)
- "rw_RW", // Kinyarwanda (Rwanda)
- "sa_IN", // Sanskrit (India)
- "sat_IN", // Santali (India)
- "sc_IT", // Sardinian (Italy)
- "sco", // Scots
- "sd_IN", // Sindhi (India)
- "se_NO", // Northern Sami (Norway)
- "sgs_LT", // Samogitian (Lithuania)
- "shs_CA", // Shuswap (Canada)
- "sid_ET", // Sidamo (Ethiopia)
- "si", // Sinhala
- "si_LK", // Sinhala (Sri Lanka)
- "sk", // Slovak
- "sk_SK", // Slovak (Slovakia)
- "sl", // Slovenian
- "sl_SI", // Slovenian (Slovenia)
- "so", // Somali
- "so_DJ", // Somali (Djibouti)
- "so_ET", // Somali (Ethiopia)
- "so_KE", // Somali (Kenya)
- "so_SO", // Somali (Somalia)
- "son_ML", // Songhai languages (Mali)
- "sq", // Albanian
- "sq_AL", // Albanian (Albania)
- "sq_KV", // Albanian (Kosovo)
- "sq_MK", // Albanian (Macedonia)
- "sr", // Serbian
- "sr_Cyrl", // Serbian (Cyrillic)
- "sr_Latn", // Serbian (Latin)
- "sr_ME", // Serbian (Montenegro)
- "sr_RS", // Serbian (Serbia)
- "ss_ZA", // Swati (South Africa)
- "st_ZA", // Southern Sotho (South Africa)
- "sv", // Swedish
- "sv_FI", // Swedish (Finland)
- "sv_SE", // Swedish (Sweden)
- "sw_KE", // Swahili (Kenya)
- "sw_TZ", // Swahili (Tanzania)
- "szl_PL", // Silesian (Poland)
- "ta", // Tamil
- "ta_IN", // Tamil (India)
- "ta_LK", // Tamil (Sri Lanka)
- "tcy_IN", // Tulu (India)
- "te", // Telugu
- "te_IN", // Telugu (India)
- "tg_TJ", // Tajik (Tajikistan)
- "the_NP", // Chitwania Tharu (Nepal)
- "th", // Thai
- "th_TH", // Thai (Thailand)
- "ti", // Tigrinya
- "ti_ER", // Tigrinya (Eritrea)
- "ti_ET", // Tigrinya (Ethiopia)
- "tig_ER", // Tigre (Eritrea)
- "tk_TM", // Turkmen (Turkmenistan)
- "tl_PH", // Tagalog (Philippines)
- "tn_ZA", // Tswana (South Africa)
- "tr", // Turkish
- "tr_CY", // Turkish (Cyprus)
- "tr_TR", // Turkish (Turkey)
- "ts_ZA", // Tsonga (South Africa)
- "tt", // Tatar
- "tt_RU", // Tatar (Russia)
- "tzm", // Central Atlas Tamazight
- "tzm_MA", // Central Atlas Tamazight (Marrocos)
- "ug_CN", // Uighur (China)
- "uk", // Ukrainian
- "uk_UA", // Ukrainian (Ukraine)
- "unm_US", // Unami (United States)
- "ur", // Urdu
- "ur_IN", // Urdu (India)
- "ur_PK", // Urdu (Pakistan)
- "uz", // Uzbek
- "uz_UZ", // Uzbek (Uzbekistan)
- "ve_ZA", // Venda (South Africa)
- "vi", // Vietnamese
- "vi_VN", // Vietnamese (Vietnam)
- "wa_BE", // Walloon (Belgium)
- "wae_CH", // Walser (Switzerland)
- "wal_ET", // Wolaytta (Ethiopia)
- "wo_SN", // Wolof (Senegal)
- "xh_ZA", // Xhosa (South Africa)
- "yi_US", // Yiddish (United States)
- "yo_NG", // Yoruba (Nigeria)
- "yue_HK", // Yue Chinese (Hong Kong)
- "zh", // Chinese
- "zh_CN", // Chinese (China)
- "zh_HK", // Chinese (Hong Kong)
- "zh_SG", // Chinese (Singapore)
- "zh_TW", // Chinese (Taiwan)
- "zu_ZA", // Zulu (South Africa)
- nullptr
-};
-
-static const char *locale_names[] = {
- "Afar",
- "Afar (Djibouti)",
- "Afar (Eritrea)",
- "Afar (Ethiopia)",
- "Afrikaans",
- "Afrikaans (South Africa)",
- "Aguaruna (Peru)",
- "Akan (Ghana)",
- "Amharic (Ethiopia)",
- "Aragonese (Spain)",
- "Angika (India)",
- "Arabic",
- "Arabic (United Arab Emirates)",
- "Arabic (Bahrain)",
- "Arabic (Algeria)",
- "Arabic (Egypt)",
- "Arabic (India)",
- "Arabic (Iraq)",
- "Arabic (Jordan)",
- "Arabic (Kuwait)",
- "Arabic (Lebanon)",
- "Arabic (Libya)",
- "Arabic (Morocco)",
- "Arabic (Oman)",
- "Arabic (Qatar)",
- "Arabic (Saudi Arabia)",
- "Arabic (Sudan)",
- "Arabic (South Soudan)",
- "Arabic (Syria)",
- "Arabic (Tunisia)",
- "Arabic (Yemen)",
- "Assamese (India)",
- "Asturian (Spain)",
- "Southern Aymara (Peru)",
- "Aymara (Peru)",
- "Azerbaijani",
- "Azerbaijani (Azerbaijan)",
- "Belarusian",
- "Belarusian (Belarus)",
- "Bemba (Zambia)",
- "Berber languages (Algeria)",
- "Berber languages (Morocco)",
- "Bulgarian",
- "Bulgarian (Bulgaria)",
- "Bhili (India)",
- "Bhojpuri (India)",
- "Bislama (Tuvalu)",
- "Bengali",
- "Bengali (Bangladesh)",
- "Bengali (India)",
- "Tibetan",
- "Tibetan (China)",
- "Tibetan (India)",
- "Breton",
- "Breton (France)",
- "Bodo (India)",
- "Bosnian (Bosnia and Herzegovina)",
- "Bilin (Eritrea)",
- "Catalan",
- "Catalan (Andorra)",
- "Catalan (Spain)",
- "Catalan (France)",
- "Catalan (Italy)",
- "Chechen (Russia)",
- "Cherokee (United States)",
- "Mandarin Chinese (Taiwan)",
- "Crimean Tatar (Ukraine)",
- "Kashubian (Poland)",
- "Czech",
- "Czech (Czech Republic)",
- "Chuvash (Russia)",
- "Welsh (United Kingdom)",
- "Danish",
- "Danish (Denmark)",
- "German",
- "German (Austria)",
- "German (Belgium)",
- "German (Switzerland)",
- "German (Germany)",
- "German (Italy)",
- "German (Luxembourg)",
- "Dogri (India)",
- "Dhivehi (Maldives)",
- "Dzongkha (Bhutan)",
- "Greek",
- "Greek (Cyprus)",
- "Greek (Greece)",
- "English",
- "English (Antigua and Barbuda)",
- "English (Australia)",
- "English (Botswana)",
- "English (Canada)",
- "English (Denmark)",
- "English (United Kingdom)",
- "English (Hong Kong)",
- "English (Ireland)",
- "English (Israel)",
- "English (India)",
- "English (Nigeria)",
- "English (New Zealand)",
- "English (Philippines)",
- "English (Singapore)",
- "English (United States)",
- "English (South Africa)",
- "English (Zambia)",
- "English (Zimbabwe)",
- "Esperanto",
- "Spanish",
- "Spanish (Argentina)",
- "Spanish (Bolivia)",
- "Spanish (Chile)",
- "Spanish (Colombia)",
- "Spanish (Costa Rica)",
- "Spanish (Cuba)",
- "Spanish (Dominican Republic)",
- "Spanish (Ecuador)",
- "Spanish (Spain)",
- "Spanish (Guatemala)",
- "Spanish (Honduras)",
- "Spanish (Mexico)",
- "Spanish (Nicaragua)",
- "Spanish (Panama)",
- "Spanish (Peru)",
- "Spanish (Puerto Rico)",
- "Spanish (Paraguay)",
- "Spanish (El Salvador)",
- "Spanish (United States)",
- "Spanish (Uruguay)",
- "Spanish (Venezuela)",
- "Estonian",
- "Estonian (Estonia)",
- "Basque",
- "Basque (Spain)",
- "Persian",
- "Persian (Iran)",
- "Fulah (Senegal)",
- "Finnish",
- "Finnish (Finland)",
- "Filipino",
- "Filipino (Philippines)",
- "Faroese (Faroe Islands)",
- "French",
- "French (Belgium)",
- "French (Canada)",
- "French (Switzerland)",
- "French (France)",
- "French (Luxembourg)",
- "Friulian (Italy)",
- "Western Frisian (Germany)",
- "Western Frisian (Netherlands)",
- "Irish",
- "Irish (Ireland)",
- "Scottish Gaelic (United Kingdom)",
- "Geez (Eritrea)",
- "Geez (Ethiopia)",
- "Galician",
- "Galician (Spain)",
- "Gujarati (India)",
- "Manx (United Kingdom)",
- "Hakka Chinese (Taiwan)",
- "Hausa (Nigeria)",
- "Hebrew",
- "Hebrew (Israel)",
- "Hindi",
- "Hindi (India)",
- "Chhattisgarhi (India)",
- "Croatian",
- "Croatian (Croatia)",
- "Upper Sorbian (Germany)",
- "Haitian (Haiti)",
- "Hungarian",
- "Hungarian (Hungary)",
- "Huastec (Mexico)",
- "Armenian (Armenia)",
- "Interlingua (France)",
- "Indonesian",
- "Indonesian (Indonesia)",
- "Igbo (Nigeria)",
- "Inupiaq (Canada)",
- "Icelandic",
- "Icelandic (Iceland)",
- "Italian",
- "Italian (Switzerland)",
- "Italian (Italy)",
- "Inuktitut (Canada)",
- "Japanese",
- "Japanese (Japan)",
- "Kabyle (Algeria)",
- "Georgian",
- "Georgian (Georgia)",
- "Kazakh (Kazakhstan)",
- "Kalaallisut (Greenland)",
- "Central Khmer",
- "Central Khmer (Cambodia)",
- "Kannada (India)",
- "Konkani (India)",
- "Korean",
- "Korean (South Korea)",
- "Kashmiri (India)",
- "Kurdish",
- "Kurdish (Turkey)",
- "Cornish (United Kingdom)",
- "Kirghiz (Kyrgyzstan)",
- "Luxembourgish (Luxembourg)",
- "Ganda (Uganda)",
- "Limburgan (Belgium)",
- "Limburgan (Netherlands)",
- "Ligurian (Italy)",
- "Lingala (Congo)",
- "Lao (Laos)",
- "Lithuanian",
- "Lithuanian (Lithuania)",
- "Latvian",
- "Latvian (Latvia)",
- "Literary Chinese (Taiwan)",
- "Magahi (India)",
- "Maithili (India)",
- "Malagasy (Madagascar)",
- "Marshallese (Marshall Islands)",
- "Eastern Mari (Russia)",
- "Māori",
- "Māori (New Zealand)",
- "Mískito (Nicaragua)",
- "Macedonian",
- "Macedonian (Macedonia)",
- "Malayalam",
- "Malayalam (India)",
- "Manipuri (India)",
- "Mongolian (Mongolia)",
- "Marathi",
- "Marathi (India)",
- "Malay",
- "Malay (Malaysia)",
- "Maltese",
- "Maltese (Malta)",
- "Burmese (Myanmar)",
- "Erzya (Russia)",
- "Nahuatl languages (Mexico)",
- "Min Nan Chinese (Taiwan)",
- "Norwegian Bokmål",
- "Norwegian Bokmål (Norway)",
- "Low German (Germany)",
- "Low German (Netherlands)",
- "Nepali (Nepal)",
- "Central Nahuatl (Mexico)",
- "Niuean (Niue)",
- "Niuean (New Zealand)",
- "Dutch",
- "Dutch (Aruba)",
- "Dutch (Belgium)",
- "Dutch (Netherlands)",
- "Norwegian Nynorsk",
- "Norwegian Nynorsk (Norway)",
- "South Ndebele (South Africa)",
- "Pedi (South Africa)",
- "Occitan (France)",
- "Oromo",
- "Oromo (Ethiopia)",
- "Oromo (Kenya)",
- "Oriya",
- "Oriya (India)",
- "Ossetian (Russia)",
- "Panjabi (India)",
- "Papiamento",
- "Papiamento (Netherlands Antilles)",
- "Papiamento (Aruba)",
- "Papiamento (Curaçao)",
- "Panjabi (Pakistan)",
- "Polish",
- "Polish (Poland)",
- "Pirate",
- "Pushto (Afghanistan)",
- "Portuguese",
- "Portuguese (Brazil)",
- "Portuguese (Portugal)",
- "Ayacucho Quechua (Peru)",
- "Cusco Quechua (Peru)",
- "Rajasthani (India)",
- "Romanian",
- "Romanian (Romania)",
- "Russian",
- "Russian (Russia)",
- "Russian (Ukraine)",
- "Kinyarwanda (Rwanda)",
- "Sanskrit (India)",
- "Santali (India)",
- "Sardinian (Italy)",
- "Scots (Scotland)",
- "Sindhi (India)",
- "Northern Sami (Norway)",
- "Samogitian (Lithuania)",
- "Shuswap (Canada)",
- "Sidamo (Ethiopia)",
- "Sinhala",
- "Sinhala (Sri Lanka)",
- "Slovak",
- "Slovak (Slovakia)",
- "Slovenian",
- "Slovenian (Slovenia)",
- "Somali",
- "Somali (Djibouti)",
- "Somali (Ethiopia)",
- "Somali (Kenya)",
- "Somali (Somalia)",
- "Songhai languages (Mali)",
- "Albanian",
- "Albanian (Albania)",
- "Albanian (Kosovo)",
- "Albanian (Macedonia)",
- "Serbian",
- "Serbian (Cyrillic)",
- "Serbian (Latin)",
- "Serbian (Montenegro)",
- "Serbian (Serbia)",
- "Swati (South Africa)",
- "Southern Sotho (South Africa)",
- "Swedish",
- "Swedish (Finland)",
- "Swedish (Sweden)",
- "Swahili (Kenya)",
- "Swahili (Tanzania)",
- "Silesian (Poland)",
- "Tamil",
- "Tamil (India)",
- "Tamil (Sri Lanka)",
- "Tulu (India)",
- "Telugu",
- "Telugu (India)",
- "Tajik (Tajikistan)",
- "Chitwania Tharu (Nepal)",
- "Thai",
- "Thai (Thailand)",
- "Tigrinya",
- "Tigrinya (Eritrea)",
- "Tigrinya (Ethiopia)",
- "Tigre (Eritrea)",
- "Turkmen (Turkmenistan)",
- "Tagalog (Philippines)",
- "Tswana (South Africa)",
- "Turkish",
- "Turkish (Cyprus)",
- "Turkish (Turkey)",
- "Tsonga (South Africa)",
- "Tatar",
- "Tatar (Russia)",
- "Central Atlas Tamazight",
- "Central Atlas Tamazight (Marrocos)",
- "Uighur (China)",
- "Ukrainian",
- "Ukrainian (Ukraine)",
- "Unami (United States)",
- "Urdu",
- "Urdu (India)",
- "Urdu (Pakistan)",
- "Uzbek",
- "Uzbek (Uzbekistan)",
- "Venda (South Africa)",
- "Vietnamese",
- "Vietnamese (Vietnam)",
- "Walloon (Belgium)",
- "Walser (Switzerland)",
- "Wolaytta (Ethiopia)",
- "Wolof (Senegal)",
- "Xhosa (South Africa)",
- "Yiddish (United States)",
- "Yoruba (Nigeria)",
- "Yue Chinese (Hong Kong)",
- "Chinese",
- "Chinese (China)",
- "Chinese (Hong Kong)",
- "Chinese (Singapore)",
- "Chinese (Taiwan)",
- "Zulu (South Africa)",
- nullptr
-};
-
-// Windows has some weird locale identifiers which do not honor the ISO 639-1
-// standardized nomenclature. Whenever those don't conflict with existing ISO
-// identifiers, we override them.
-//
-// Reference:
-// - https://msdn.microsoft.com/en-us/library/windows/desktop/ms693062(v=vs.85).aspx
-
-static const char *locale_renames[][2] = {
- { "in", "id" }, // Indonesian
- { "iw", "he" }, // Hebrew
- { "no", "nb" }, // Norwegian Bokmål
- { "C", "en" }, // "C" is the simple/default/untranslated Computer locale.
- // ASCII-only, English, no currency symbols. Godot treats this as "en".
- // See https://unix.stackexchange.com/a/87763/164141 "The C locale is"...
- { nullptr, nullptr }
-};
-
-///////////////////////////////////////////////
-
Dictionary Translation::_get_messages() const {
Dictionary d;
for (const KeyValue<StringName, StringName> &E : translation_map) {
@@ -849,17 +68,7 @@ void Translation::_set_messages(const Dictionary &p_messages) {
}
void Translation::set_locale(const String &p_locale) {
- String univ_locale = TranslationServer::standardize_locale(p_locale);
-
- if (!TranslationServer::is_locale_valid(univ_locale)) {
- String trimmed_locale = TranslationServer::get_language_code(univ_locale);
-
- ERR_FAIL_COND_MSG(!TranslationServer::is_locale_valid(trimmed_locale), "Invalid locale: " + trimmed_locale + ".");
-
- locale = trimmed_locale;
- } else {
- locale = univ_locale;
- }
+ locale = TranslationServer::get_singleton()->standardize_locale(p_locale);
if (OS::get_singleton()->get_main_loop() && TranslationServer::get_singleton()->get_loaded_locales().has(this)) {
OS::get_singleton()->get_main_loop()->notification(MainLoop::NOTIFICATION_TRANSLATION_CHANGED);
@@ -1004,121 +213,306 @@ static _character_accent_pair _character_to_accented[] = {
{ 'z', U"ź" },
};
-bool TranslationServer::is_locale_valid(const String &p_locale) {
- const char **ptr = locale_list;
+Vector<TranslationServer::LocaleScriptInfo> TranslationServer::locale_script_info;
- while (*ptr) {
- if (*ptr == p_locale) {
- return true;
+Map<String, String> TranslationServer::language_map;
+Map<String, String> TranslationServer::script_map;
+Map<String, String> TranslationServer::locale_rename_map;
+Map<String, String> TranslationServer::country_name_map;
+Map<String, String> TranslationServer::variant_map;
+Map<String, String> TranslationServer::country_rename_map;
+
+void TranslationServer::init_locale_info() {
+ // Init locale info.
+ language_map.clear();
+ int idx = 0;
+ while (language_list[idx][0] != nullptr) {
+ language_map[language_list[idx][0]] = String::utf8(language_list[idx][1]);
+ idx++;
+ }
+
+ // Init locale-script map.
+ locale_script_info.clear();
+ idx = 0;
+ while (locale_scripts[idx][0] != nullptr) {
+ LocaleScriptInfo info;
+ info.name = locale_scripts[idx][0];
+ info.script = locale_scripts[idx][1];
+ info.default_country = locale_scripts[idx][2];
+ Vector<String> supported_countries = String(locale_scripts[idx][3]).split(",", false);
+ for (int i = 0; i < supported_countries.size(); i++) {
+ info.supported_countries.insert(supported_countries[i]);
}
- ptr++;
+ locale_script_info.push_back(info);
+ idx++;
}
- return false;
-}
+ // Init supported script list.
+ script_map.clear();
+ idx = 0;
+ while (script_list[idx][0] != nullptr) {
+ script_map[script_list[idx][1]] = String::utf8(script_list[idx][0]);
+ idx++;
+ }
-String TranslationServer::standardize_locale(const String &p_locale) {
- // Replaces '-' with '_' for macOS Sierra-style locales
- String univ_locale = p_locale.replace("-", "_");
+ // Init regional variant map.
+ variant_map.clear();
+ idx = 0;
+ while (locale_variants[idx][0] != nullptr) {
+ variant_map[locale_variants[idx][0]] = locale_variants[idx][1];
+ idx++;
+ }
- // Handles known non-ISO locale names used e.g. on Windows
- int idx = 0;
+ // Init locale renames.
+ locale_rename_map.clear();
+ idx = 0;
while (locale_renames[idx][0] != nullptr) {
- if (locale_renames[idx][0] == univ_locale) {
- univ_locale = locale_renames[idx][1];
- break;
+ if (!String(locale_renames[idx][1]).is_empty()) {
+ locale_rename_map[locale_renames[idx][0]] = locale_renames[idx][1];
}
idx++;
}
- return univ_locale;
+ // Init country names.
+ country_name_map.clear();
+ idx = 0;
+ while (country_names[idx][0] != nullptr) {
+ country_name_map[String(country_names[idx][0])] = String::utf8(country_names[idx][1]);
+ idx++;
+ }
+
+ // Init country renames.
+ country_rename_map.clear();
+ idx = 0;
+ while (country_renames[idx][0] != nullptr) {
+ if (!String(country_renames[idx][1]).is_empty()) {
+ country_rename_map[country_renames[idx][0]] = country_renames[idx][1];
+ }
+ idx++;
+ }
}
-String TranslationServer::get_language_code(const String &p_locale) {
- ERR_FAIL_COND_V_MSG(p_locale.length() < 2, p_locale, "Invalid locale '" + p_locale + "'.");
- // Most language codes are two letters, but some are three,
- // so we have to look for a regional code separator ('_' or '-')
- // to extract the left part.
- // For example we get 'nah_MX' as input and should return 'nah'.
- int split = p_locale.find("_");
- if (split == -1) {
- split = p_locale.find("-");
+String TranslationServer::standardize_locale(const String &p_locale) const {
+ // Replaces '-' with '_' for macOS style locales.
+ String univ_locale = p_locale.replace("-", "_");
+
+ // Extract locale elements.
+ String lang, script, country, variant;
+ Vector<String> locale_elements = univ_locale.get_slice("@", 0).split("_");
+ lang = locale_elements[0];
+ if (locale_elements.size() >= 2) {
+ if (locale_elements[1].length() == 4 && is_ascii_upper_case(locale_elements[1][0]) && is_ascii_lower_case(locale_elements[1][1]) && is_ascii_lower_case(locale_elements[1][2]) && is_ascii_lower_case(locale_elements[1][3])) {
+ script = locale_elements[1];
+ }
+ if (locale_elements[1].length() == 2 && is_ascii_upper_case(locale_elements[1][0]) && is_ascii_upper_case(locale_elements[1][1])) {
+ country = locale_elements[1];
+ }
}
- if (split == -1) { // No separator, so the locale is already only a language code.
- return p_locale;
+ if (locale_elements.size() >= 3) {
+ if (locale_elements[2].length() == 2 && is_ascii_upper_case(locale_elements[2][0]) && is_ascii_upper_case(locale_elements[2][1])) {
+ country = locale_elements[2];
+ } else if (variant_map.has(locale_elements[2].to_lower()) && variant_map[locale_elements[2].to_lower()] == lang) {
+ variant = locale_elements[2].to_lower();
+ }
+ }
+ if (locale_elements.size() >= 4) {
+ if (variant_map.has(locale_elements[3].to_lower()) && variant_map[locale_elements[3].to_lower()] == lang) {
+ variant = locale_elements[3].to_lower();
+ }
}
- return p_locale.left(split);
-}
-void TranslationServer::set_locale(const String &p_locale) {
- String univ_locale = standardize_locale(p_locale);
+ // Try extract script and variant from the extra part.
+ Vector<String> script_extra = univ_locale.get_slice("@", 1).split(";");
+ for (int i = 0; i < script_extra.size(); i++) {
+ if (script_extra[i].to_lower() == "cyrillic") {
+ script = "Cyrl";
+ break;
+ } else if (script_extra[i].to_lower() == "latin") {
+ script = "Latn";
+ break;
+ } else if (script_extra[i].to_lower() == "devanagari") {
+ script = "Deva";
+ break;
+ } else if (variant_map.has(script_extra[i].to_lower()) && variant_map[script_extra[i].to_lower()] == lang) {
+ variant = script_extra[i].to_lower();
+ }
+ }
- if (!is_locale_valid(univ_locale)) {
- String trimmed_locale = get_language_code(univ_locale);
- print_verbose(vformat("Unsupported locale '%s', falling back to '%s'.", p_locale, trimmed_locale));
+ // Handles known non-ISO language names used e.g. on Windows.
+ if (locale_rename_map.has(lang)) {
+ lang = locale_rename_map[lang];
+ }
- if (!is_locale_valid(trimmed_locale)) {
- ERR_PRINT(vformat("Unsupported locale '%s', falling back to 'en'.", trimmed_locale));
- locale = "en";
- } else {
- locale = trimmed_locale;
+ // Handle country renames.
+ if (country_rename_map.has(country)) {
+ country = country_rename_map[country];
+ }
+
+ // Remove unsupported script codes.
+ if (!script_map.has(script)) {
+ script = "";
+ }
+
+ // Add script code base on language and country codes for some ambiguous cases.
+ if (script.is_empty()) {
+ for (int i = 0; i < locale_script_info.size(); i++) {
+ const LocaleScriptInfo &info = locale_script_info[i];
+ if (info.name == lang) {
+ if (country.is_empty() || info.supported_countries.has(country)) {
+ script = info.script;
+ break;
+ }
+ }
}
+ }
+ if (!script.is_empty() && country.is_empty()) {
+ // Add conntry code based on script for some ambiguous cases.
+ for (int i = 0; i < locale_script_info.size(); i++) {
+ const LocaleScriptInfo &info = locale_script_info[i];
+ if (info.name == lang && info.script == script) {
+ country = info.default_country;
+ break;
+ }
+ }
+ }
+
+ // Combine results.
+ String locale = lang;
+ if (!script.is_empty()) {
+ locale = locale + "_" + script;
+ }
+ if (!country.is_empty()) {
+ locale = locale + "_" + country;
+ }
+ if (!variant.is_empty()) {
+ locale = locale + "_" + variant;
+ }
+ return locale;
+}
+
+int TranslationServer::compare_locales(const String &p_locale_a, const String &p_locale_b) const {
+ String locale_a = standardize_locale(p_locale_a);
+ String locale_b = standardize_locale(p_locale_b);
+
+ if (locale_a == locale_b) {
+ // Exact match.
+ return 10;
+ }
+
+ Vector<String> locale_a_elements = locale_a.split("_");
+ Vector<String> locale_b_elements = locale_b.split("_");
+ if (locale_a_elements[0] == locale_b_elements[0]) {
+ // Matching language, both locales have extra parts.
+ // Return number of matching elements.
+ int matching_elements = 1;
+ for (int i = 1; i < locale_a_elements.size(); i++) {
+ for (int j = 1; j < locale_b_elements.size(); j++) {
+ if (locale_a_elements[i] == locale_b_elements[j]) {
+ matching_elements++;
+ }
+ }
+ }
+ return matching_elements;
} else {
- locale = univ_locale;
+ // No match.
+ return 0;
}
+}
- if (OS::get_singleton()->get_main_loop()) {
- OS::get_singleton()->get_main_loop()->notification(MainLoop::NOTIFICATION_TRANSLATION_CHANGED);
+String TranslationServer::get_locale_name(const String &p_locale) const {
+ String locale = standardize_locale(p_locale);
+
+ String lang, script, country;
+ Vector<String> locale_elements = locale.split("_");
+ lang = locale_elements[0];
+ if (locale_elements.size() >= 2) {
+ if (locale_elements[1].length() == 4 && is_ascii_upper_case(locale_elements[1][0]) && is_ascii_lower_case(locale_elements[1][1]) && is_ascii_lower_case(locale_elements[1][2]) && is_ascii_lower_case(locale_elements[1][3])) {
+ script = locale_elements[1];
+ }
+ if (locale_elements[1].length() == 2 && is_ascii_upper_case(locale_elements[1][0]) && is_ascii_upper_case(locale_elements[1][1])) {
+ country = locale_elements[1];
+ }
+ }
+ if (locale_elements.size() >= 3) {
+ if (locale_elements[2].length() == 2 && is_ascii_upper_case(locale_elements[2][0]) && is_ascii_upper_case(locale_elements[2][1])) {
+ country = locale_elements[2];
+ }
}
- ResourceLoader::reload_translation_remaps();
+ String name = language_map[lang];
+ if (!script.is_empty()) {
+ name = name + " (" + script_map[script] + ")";
+ }
+ if (!country.is_empty()) {
+ name = name + ", " + country_name_map[country];
+ }
+ return name;
}
-String TranslationServer::get_locale() const {
- return locale;
+Vector<String> TranslationServer::get_all_languages() const {
+ Vector<String> languages;
+
+ for (const Map<String, String>::Element *E = language_map.front(); E; E = E->next()) {
+ languages.push_back(E->key());
+ }
+
+ return languages;
}
-String TranslationServer::get_locale_name(const String &p_locale) const {
- if (!locale_name_map.has(p_locale)) {
- return String();
+String TranslationServer::get_language_name(const String &p_language) const {
+ return language_map[p_language];
+}
+
+Vector<String> TranslationServer::get_all_scripts() const {
+ Vector<String> scripts;
+
+ for (const Map<String, String>::Element *E = script_map.front(); E; E = E->next()) {
+ scripts.push_back(E->key());
}
- return locale_name_map[p_locale];
+
+ return scripts;
}
-Array TranslationServer::get_loaded_locales() const {
- Array locales;
- for (const Set<Ref<Translation>>::Element *E = translations.front(); E; E = E->next()) {
- const Ref<Translation> &t = E->get();
- ERR_FAIL_COND_V(t.is_null(), Array());
- String l = t->get_locale();
+String TranslationServer::get_script_name(const String &p_script) const {
+ return script_map[p_script];
+}
- locales.push_back(l);
+Vector<String> TranslationServer::get_all_countries() const {
+ Vector<String> countries;
+
+ for (const Map<String, String>::Element *E = country_name_map.front(); E; E = E->next()) {
+ countries.push_back(E->key());
}
- return locales;
+ return countries;
}
-Vector<String> TranslationServer::get_all_locales() {
- Vector<String> locales;
+String TranslationServer::get_country_name(const String &p_country) const {
+ return country_name_map[p_country];
+}
- const char **ptr = locale_list;
+void TranslationServer::set_locale(const String &p_locale) {
+ locale = standardize_locale(p_locale);
- while (*ptr) {
- locales.push_back(*ptr);
- ptr++;
+ if (OS::get_singleton()->get_main_loop()) {
+ OS::get_singleton()->get_main_loop()->notification(MainLoop::NOTIFICATION_TRANSLATION_CHANGED);
}
- return locales;
+ ResourceLoader::reload_translation_remaps();
}
-Vector<String> TranslationServer::get_all_locale_names() {
- Vector<String> locales;
+String TranslationServer::get_locale() const {
+ return locale;
+}
- const char **ptr = locale_names;
+Array TranslationServer::get_loaded_locales() const {
+ Array locales;
+ for (const Set<Ref<Translation>>::Element *E = translations.front(); E; E = E->next()) {
+ const Ref<Translation> &t = E->get();
+ ERR_FAIL_COND_V(t.is_null(), Array());
+ String l = t->get_locale();
- while (*ptr) {
- locales.push_back(String::utf8(*ptr));
- ptr++;
+ locales.push_back(l);
}
return locales;
@@ -1134,23 +528,20 @@ void TranslationServer::remove_translation(const Ref<Translation> &p_translation
Ref<Translation> TranslationServer::get_translation_object(const String &p_locale) {
Ref<Translation> res;
- String lang = get_language_code(p_locale);
- bool near_match_found = false;
+ int best_score = 0;
for (const Set<Ref<Translation>>::Element *E = translations.front(); E; E = E->next()) {
const Ref<Translation> &t = E->get();
ERR_FAIL_COND_V(t.is_null(), nullptr);
String l = t->get_locale();
- // Exact match.
- if (l == p_locale) {
- return t;
- }
-
- // If near match found, keep that match, but keep looking to try to look for perfect match.
- if (get_language_code(l) == lang && !near_match_found) {
+ int score = compare_locales(p_locale, l);
+ if (score > 0 && score >= best_score) {
res = t;
- near_match_found = true;
+ best_score = score;
+ if (score == 10) {
+ break; // Exact match, skip the rest.
+ }
}
}
return res;
@@ -1167,8 +558,6 @@ StringName TranslationServer::translate(const StringName &p_message, const Strin
return p_message;
}
- ERR_FAIL_COND_V_MSG(locale.length() < 2, p_message, "Could not translate message as configured locale '" + locale + "' is invalid.");
-
StringName res = _get_message_from_translations(p_message, p_context, locale, false);
if (!res && fallback.length() >= 2) {
@@ -1190,8 +579,6 @@ StringName TranslationServer::translate_plural(const StringName &p_message, cons
return p_message_plural;
}
- ERR_FAIL_COND_V_MSG(locale.length() < 2, p_message, "Could not translate message as configured locale '" + locale + "' is invalid.");
-
StringName res = _get_message_from_translations(p_message, p_context, locale, true, p_message_plural, p_n);
if (!res && fallback.length() >= 2) {
@@ -1209,51 +596,30 @@ StringName TranslationServer::translate_plural(const StringName &p_message, cons
}
StringName TranslationServer::_get_message_from_translations(const StringName &p_message, const StringName &p_context, const String &p_locale, bool plural, const String &p_message_plural, int p_n) const {
- // Locale can be of the form 'll_CC', i.e. language code and regional code,
- // e.g. 'en_US', 'en_GB', etc. It might also be simply 'll', e.g. 'en'.
- // To find the relevant translation, we look for those with locale starting
- // with the language code, and then if any is an exact match for the long
- // form. If not found, we fall back to a near match (another locale with
- // same language code).
-
- // Note: ResourceLoader::_path_remap reproduces this locale near matching
- // logic, so be sure to propagate changes there when changing things here.
-
StringName res;
- String lang = get_language_code(p_locale);
- bool near_match = false;
+ int best_score = 0;
for (const Set<Ref<Translation>>::Element *E = translations.front(); E; E = E->next()) {
const Ref<Translation> &t = E->get();
ERR_FAIL_COND_V(t.is_null(), p_message);
String l = t->get_locale();
- bool exact_match = (l == p_locale);
- if (!exact_match) {
- if (near_match) {
- continue; // Only near-match once, but keep looking for exact matches.
+ int score = compare_locales(p_locale, l);
+ if (score > 0 && score >= best_score) {
+ StringName r;
+ if (!plural) {
+ r = t->get_message(p_message, p_context);
+ } else {
+ r = t->get_plural_message(p_message, p_message_plural, p_n, p_context);
}
- if (get_language_code(l) != lang) {
- continue; // Language code does not match.
+ if (!r) {
+ continue;
+ }
+ res = r;
+ best_score = score;
+ if (score == 10) {
+ break; // Exact match, skip the rest.
}
- }
-
- StringName r;
- if (!plural) {
- r = t->get_message(p_message, p_context);
- } else {
- r = t->get_plural_message(p_message, p_message_plural, p_n, p_context);
- }
-
- if (!r) {
- continue;
- }
- res = r;
-
- if (exact_match) {
- break;
- } else {
- near_match = true;
}
}
@@ -1287,7 +653,7 @@ bool TranslationServer::_load_translations(const String &p_from) {
void TranslationServer::setup() {
String test = GLOBAL_DEF("internationalization/locale/test", "");
test = test.strip_edges();
- if (test != "") {
+ if (!test.is_empty()) {
set_locale(test);
} else {
set_locale(OS::get_singleton()->get_locale());
@@ -1305,18 +671,7 @@ void TranslationServer::setup() {
pseudolocalization_skip_placeholders_enabled = GLOBAL_DEF("internationalization/pseudolocalization/skip_placeholders", true);
#ifdef TOOLS_ENABLED
- {
- String options = "";
- int idx = 0;
- while (locale_list[idx]) {
- if (idx > 0) {
- options += ",";
- }
- options += locale_list[idx];
- idx++;
- }
- ProjectSettings::get_singleton()->set_custom_property_info("internationalization/locale/fallback", PropertyInfo(Variant::STRING, "internationalization/locale/fallback", PROPERTY_HINT_ENUM, options));
- }
+ ProjectSettings::get_singleton()->set_custom_property_info("internationalization/locale/fallback", PropertyInfo(Variant::STRING, "internationalization/locale/fallback", PROPERTY_HINT_LOCALE_ID, ""));
#endif
}
@@ -1330,8 +685,12 @@ Ref<Translation> TranslationServer::get_tool_translation() const {
String TranslationServer::get_tool_locale() {
#ifdef TOOLS_ENABLED
- if (TranslationServer::get_singleton()->get_tool_translation().is_valid() && (Engine::get_singleton()->is_editor_hint() || Main::is_project_manager())) {
- return tool_translation->get_locale();
+ if (Engine::get_singleton()->is_editor_hint() || Engine::get_singleton()->is_project_manager_hint()) {
+ if (TranslationServer::get_singleton()->get_tool_translation().is_valid()) {
+ return tool_translation->get_locale();
+ } else {
+ return "en";
+ }
} else {
#else
{
@@ -1548,7 +907,7 @@ String TranslationServer::add_padding(String &p_message, int p_length) const {
}
const char32_t *TranslationServer::get_accented_version(char32_t p_character) const {
- if (!((p_character >= 'a' && p_character <= 'z') || (p_character >= 'A' && p_character <= 'Z'))) {
+ if (!is_ascii_char(p_character)) {
return nullptr;
}
@@ -1570,6 +929,19 @@ bool TranslationServer::is_placeholder(String &p_message, int p_index) const {
void TranslationServer::_bind_methods() {
ClassDB::bind_method(D_METHOD("set_locale", "locale"), &TranslationServer::set_locale);
ClassDB::bind_method(D_METHOD("get_locale"), &TranslationServer::get_locale);
+ ClassDB::bind_method(D_METHOD("get_tool_locale"), &TranslationServer::get_tool_locale);
+
+ ClassDB::bind_method(D_METHOD("compare_locales", "locale_a", "locale_b"), &TranslationServer::compare_locales);
+ ClassDB::bind_method(D_METHOD("standardize_locale", "locale"), &TranslationServer::standardize_locale);
+
+ ClassDB::bind_method(D_METHOD("get_all_languages"), &TranslationServer::get_all_languages);
+ ClassDB::bind_method(D_METHOD("get_language_name", "language"), &TranslationServer::get_language_name);
+
+ ClassDB::bind_method(D_METHOD("get_all_scripts"), &TranslationServer::get_all_scripts);
+ ClassDB::bind_method(D_METHOD("get_script_name", "script"), &TranslationServer::get_script_name);
+
+ ClassDB::bind_method(D_METHOD("get_all_countries"), &TranslationServer::get_all_countries);
+ ClassDB::bind_method(D_METHOD("get_country_name", "country"), &TranslationServer::get_country_name);
ClassDB::bind_method(D_METHOD("get_locale_name", "locale"), &TranslationServer::get_locale_name);
@@ -1603,8 +975,5 @@ void TranslationServer::load_translations() {
TranslationServer::TranslationServer() {
singleton = this;
-
- for (int i = 0; locale_list[i]; ++i) {
- locale_name_map.insert(locale_list[i], String::utf8(locale_names[i]));
- }
+ init_locale_info();
}
diff --git a/core/string/translation.h b/core/string/translation.h
index 6aec0bb8ea..947ca4c6d8 100644
--- a/core/string/translation.h
+++ b/core/string/translation.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -78,8 +78,6 @@ class TranslationServer : public Object {
Ref<Translation> tool_translation;
Ref<Translation> doc_translation;
- Map<String, String> locale_name_map;
-
bool enabled = true;
bool pseudolocalization_enabled = false;
@@ -109,6 +107,23 @@ class TranslationServer : public Object {
static void _bind_methods();
+ struct LocaleScriptInfo {
+ String name;
+ String script;
+ String default_country;
+ Set<String> supported_countries;
+ };
+ static Vector<LocaleScriptInfo> locale_script_info;
+
+ static Map<String, String> language_map;
+ static Map<String, String> script_map;
+ static Map<String, String> locale_rename_map;
+ static Map<String, String> country_name_map;
+ static Map<String, String> country_rename_map;
+ static Map<String, String> variant_map;
+
+ void init_locale_info();
+
public:
_FORCE_INLINE_ static TranslationServer *get_singleton() { return singleton; }
@@ -119,6 +134,15 @@ public:
String get_locale() const;
Ref<Translation> get_translation_object(const String &p_locale);
+ Vector<String> get_all_languages() const;
+ String get_language_name(const String &p_language) const;
+
+ Vector<String> get_all_scripts() const;
+ String get_script_name(const String &p_script) const;
+
+ Vector<String> get_all_countries() const;
+ String get_country_name(const String &p_country) const;
+
String get_locale_name(const String &p_locale) const;
Array get_loaded_locales() const;
@@ -136,11 +160,9 @@ public:
void set_editor_pseudolocalization(bool p_enabled);
void reload_pseudolocalization();
- static Vector<String> get_all_locales();
- static Vector<String> get_all_locale_names();
- static bool is_locale_valid(const String &p_locale);
- static String standardize_locale(const String &p_locale);
- static String get_language_code(const String &p_locale);
+ String standardize_locale(const String &p_locale) const;
+
+ int compare_locales(const String &p_locale_a, const String &p_locale_b) const;
String get_tool_locale();
void set_tool_translation(const Ref<Translation> &p_translation);
diff --git a/core/string/translation_po.cpp b/core/string/translation_po.cpp
index 1da00aa54b..1c991ee12d 100644
--- a/core/string/translation_po.cpp
+++ b/core/string/translation_po.cpp
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/translation_po.h b/core/string/translation_po.h
index 0e1d03d6ca..7d63af2246 100644
--- a/core/string/translation_po.h
+++ b/core/string/translation_po.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/ucaps.h b/core/string/ucaps.h
index b785ac7879..357d36e703 100644
--- a/core/string/ucaps.h
+++ b/core/string/ucaps.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
diff --git a/core/string/ustring.cpp b/core/string/ustring.cpp
index 320aae2ba4..759c121f29 100644
--- a/core/string/ustring.cpp
+++ b/core/string/ustring.cpp
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -54,34 +54,14 @@
static const int MAX_DECIMALS = 32;
-static _FORCE_INLINE_ bool is_digit(char32_t c) {
- return (c >= '0' && c <= '9');
-}
-
-static _FORCE_INLINE_ bool is_hex_digit(char32_t c) {
- return (is_digit(c) || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'));
-}
-
-static _FORCE_INLINE_ bool is_upper_case(char32_t c) {
- return (c >= 'A' && c <= 'Z');
-}
-
-static _FORCE_INLINE_ bool is_lower_case(char32_t c) {
- return (c >= 'a' && c <= 'z');
-}
-
static _FORCE_INLINE_ char32_t lower_case(char32_t c) {
- return (is_upper_case(c) ? (c + ('a' - 'A')) : c);
+ return (is_ascii_upper_case(c) ? (c + ('a' - 'A')) : c);
}
const char CharString::_null = 0;
const char16_t Char16String::_null = 0;
const char32_t String::_null = 0;
-bool is_symbol(char32_t c) {
- return c != '_' && ((c >= '!' && c <= '/') || (c >= ':' && c <= '@') || (c >= '[' && c <= '`') || (c >= '{' && c <= '~') || c == '\t' || c == ' ');
-}
-
bool select_word(const String &p_s, int p_col, int &r_beg, int &r_end) {
const String &s = p_s;
int beg = CLAMP(p_col, 0, s.length());
@@ -123,16 +103,18 @@ bool Char16String::operator<(const Char16String &p_right) const {
}
Char16String &Char16String::operator+=(char16_t p_char) {
- resize(size() ? size() + 1 : 2);
- set(length(), 0);
- set(length() - 1, p_char);
+ const int lhs_len = length();
+ resize(lhs_len + 2);
+
+ char16_t *dst = ptrw();
+ dst[lhs_len] = p_char;
+ dst[lhs_len + 1] = 0;
return *this;
}
-Char16String &Char16String::operator=(const char16_t *p_cstr) {
+void Char16String::operator=(const char16_t *p_cstr) {
copy_from(p_cstr);
- return *this;
}
const char16_t *Char16String::get_data() const {
@@ -179,16 +161,18 @@ bool CharString::operator<(const CharString &p_right) const {
}
CharString &CharString::operator+=(char p_char) {
- resize(size() ? size() + 1 : 2);
- set(length(), 0);
- set(length() - 1, p_char);
+ const int lhs_len = length();
+ resize(lhs_len + 2);
+
+ char *dst = ptrw();
+ dst[lhs_len] = p_char;
+ dst[lhs_len + 1] = 0;
return *this;
}
-CharString &CharString::operator=(const char *p_cstr) {
+void CharString::operator=(const char *p_cstr) {
copy_from(p_cstr);
- return *this;
}
const char *CharString::get_data() const {
@@ -326,11 +310,7 @@ void String::copy_from(const char *p_cstr) {
return;
}
- int len = 0;
- const char *ptr = p_cstr;
- while (*(ptr++) != 0) {
- len++;
- }
+ const size_t len = strlen(p_cstr);
if (len == 0) {
resize(0);
@@ -341,7 +321,7 @@ void String::copy_from(const char *p_cstr) {
char32_t *dst = this->ptrw();
- for (int i = 0; i < len + 1; i++) {
+ for (size_t i = 0; i <= len; i++) {
dst[i] = p_cstr[i];
}
}
@@ -396,13 +376,14 @@ void String::copy_from(const wchar_t *p_cstr, const int p_clip_to) {
void String::copy_from(const char32_t &p_char) {
resize(2);
+ char32_t *dst = ptrw();
if ((p_char >= 0xd800 && p_char <= 0xdfff) || (p_char > 0x10ffff)) {
print_error("Unicode parsing error: Invalid unicode codepoint " + num_int64(p_char, 16) + ".");
- set(0, 0xfffd);
+ dst[0] = 0xfffd;
} else {
- set(0, p_char);
+ dst[0] = p_char;
}
- set(1, 0);
+ dst[1] = 0;
}
void String::copy_from(const char32_t *p_cstr) {
@@ -451,9 +432,8 @@ void String::copy_from(const char32_t *p_cstr, const int p_clip_to) {
// p_length <= p_char strlen
void String::copy_from_unchecked(const char32_t *p_char, const int p_length) {
resize(p_length + 1);
- set(p_length, 0);
-
char32_t *dst = ptrw();
+ dst[p_length] = 0;
for (int i = 0; i < p_length; i++) {
if ((p_char[i] >= 0xd800 && p_char[i] <= 0xdfff) || (p_char[i] > 0x10ffff)) {
@@ -506,27 +486,23 @@ String operator+(char32_t p_chr, const String &p_str) {
}
String &String::operator+=(const String &p_str) {
- if (is_empty()) {
+ const int lhs_len = length();
+ if (lhs_len == 0) {
*this = p_str;
return *this;
}
- if (p_str.is_empty()) {
+ const int rhs_len = p_str.length();
+ if (rhs_len == 0) {
return *this;
}
- int from = length();
-
- resize(length() + p_str.size());
+ resize(lhs_len + rhs_len + 1);
const char32_t *src = p_str.get_data();
- char32_t *dst = ptrw();
+ char32_t *dst = ptrw() + lhs_len;
- set(length(), 0);
-
- for (int i = 0; i < p_str.length(); i++) {
- dst[from + i] = src[i];
- }
+ memcpy(dst, src, (rhs_len + 1) * sizeof(char32_t));
return *this;
}
@@ -536,22 +512,15 @@ String &String::operator+=(const char *p_str) {
return *this;
}
- int src_len = 0;
- const char *ptr = p_str;
- while (*(ptr++) != 0) {
- src_len++;
- }
-
- int from = length();
+ const int lhs_len = length();
+ const size_t rhs_len = strlen(p_str);
- resize(from + src_len + 1);
+ resize(lhs_len + rhs_len + 1);
- char32_t *dst = ptrw();
+ char32_t *dst = ptrw() + lhs_len;
- set(length(), 0);
-
- for (int i = 0; i < src_len; i++) {
- dst[from + i] = p_str[i];
+ for (size_t i = 0; i <= rhs_len; i++) {
+ dst[i] = p_str[i];
}
return *this;
@@ -574,14 +543,16 @@ String &String::operator+=(const char32_t *p_str) {
}
String &String::operator+=(char32_t p_char) {
- resize(size() ? size() + 1 : 2);
- set(length(), 0);
+ const int lhs_len = length();
+ resize(lhs_len + 2);
+ char32_t *dst = ptrw();
if ((p_char >= 0xd800 && p_char <= 0xdfff) || (p_char > 0x10ffff)) {
print_error("Unicode parsing error: Invalid unicode codepoint " + num_int64(p_char, 16) + ".");
- set(length() - 1, 0xfffd);
+ dst[lhs_len] = 0xfffd;
} else {
- set(length() - 1, p_char);
+ dst[lhs_len] = p_char;
}
+ dst[lhs_len + 1] = 0;
return *this;
}
@@ -976,21 +947,21 @@ String String::camelcase_to_underscore(bool lowercase) const {
int start_index = 0;
for (int i = 1; i < this->size(); i++) {
- bool is_upper = is_upper_case(cstr[i]);
+ bool is_upper = is_ascii_upper_case(cstr[i]);
bool is_number = is_digit(cstr[i]);
bool are_next_2_lower = false;
bool is_next_lower = false;
bool is_next_number = false;
- bool was_precedent_upper = is_upper_case(cstr[i - 1]);
+ bool was_precedent_upper = is_ascii_upper_case(cstr[i - 1]);
bool was_precedent_number = is_digit(cstr[i - 1]);
if (i + 2 < this->size()) {
- are_next_2_lower = is_lower_case(cstr[i + 1]) && is_lower_case(cstr[i + 2]);
+ are_next_2_lower = is_ascii_lower_case(cstr[i + 1]) && is_ascii_lower_case(cstr[i + 2]);
}
if (i + 1 < this->size()) {
- is_next_lower = is_lower_case(cstr[i + 1]);
+ is_next_lower = is_ascii_lower_case(cstr[i + 1]);
is_next_number = is_digit(cstr[i + 1]);
}
@@ -1529,115 +1500,24 @@ String String::num_uint64(uint64_t p_num, int base, bool capitalize_hex) {
}
String String::num_real(double p_num, bool p_trailing) {
- if (Math::is_nan(p_num)) {
- return "nan";
- }
-
- if (Math::is_inf(p_num)) {
- if (signbit(p_num)) {
- return "-inf";
+ if (p_num == (double)(int64_t)p_num) {
+ if (p_trailing) {
+ return num_int64((int64_t)p_num) + ".0";
} else {
- return "inf";
+ return num_int64((int64_t)p_num);
}
}
-
- String s;
- String sd;
-
- // Integer part.
-
- bool neg = p_num < 0;
- p_num = ABS(p_num);
- int64_t intn = (int64_t)p_num;
-
- // Decimal part.
-
- if (intn != p_num) {
- double dec = p_num - (double)intn;
-
- int digit = 0;
-
#ifdef REAL_T_IS_DOUBLE
- int decimals = 14;
- double tolerance = 1e-14;
+ int decimals = 14;
#else
- int decimals = 6;
- double tolerance = 1e-6;
+ int decimals = 6;
#endif
- // We want to align the digits to the above sane default, so we only
- // need to subtract log10 for numbers with a positive power of ten.
- if (p_num > 10) {
- decimals -= (int)floor(log10(p_num));
- }
-
- if (decimals > MAX_DECIMALS) {
- decimals = MAX_DECIMALS;
- }
-
- // In case the value ends up ending in "99999", we want to add a
- // tiny bit to the value we're checking when deciding when to stop,
- // so we multiply by slightly above 1 (1 + 1e-7 or 1e-15).
- double check_multiplier = 1 + tolerance / 10;
-
- int64_t dec_int = 0;
- int64_t dec_max = 0;
-
- while (true) {
- dec *= 10.0;
- dec_int = dec_int * 10 + (int64_t)dec % 10;
- dec_max = dec_max * 10 + 9;
- digit++;
-
- if ((dec - (double)(int64_t)(dec * check_multiplier)) < tolerance) {
- break;
- }
-
- if (digit == decimals) {
- break;
- }
- }
-
- dec *= 10;
- int last = (int64_t)dec % 10;
-
- if (last > 5) {
- if (dec_int == dec_max) {
- dec_int = 0;
- intn++;
- } else {
- dec_int++;
- }
- }
-
- String decimal;
- for (int i = 0; i < digit; i++) {
- char num[2] = { 0, 0 };
- num[0] = '0' + dec_int % 10;
- decimal = num + decimal;
- dec_int /= 10;
- }
- sd = '.' + decimal;
- } else if (p_trailing) {
- sd = ".0";
- } else {
- sd = "";
- }
-
- if (intn == 0) {
- s = "0";
- } else {
- while (intn) {
- char32_t num = '0' + (intn % 10);
- intn /= 10;
- s = num + s;
- }
+ // We want to align the digits to the above sane default, so we only
+ // need to subtract log10 for numbers with a positive power of ten.
+ if (p_num > 10) {
+ decimals -= (int)floor(log10(p_num));
}
-
- s = s + sd;
- if (neg) {
- s = "-" + s;
- }
- return s;
+ return num(p_num, decimals);
}
String String::num_scientific(double p_num) {
@@ -1725,7 +1605,7 @@ String String::utf8(const char *p_utf8, int p_len) {
}
bool String::parse_utf8(const char *p_utf8, int p_len) {
-#define _UNICERROR(m_err) print_error("Unicode parsing error: " + String(m_err) + ". Is the string valid UTF-8?");
+#define UNICERROR(m_err) print_error("Unicode parsing error: " + String(m_err) + ". Is the string valid UTF-8?");
if (!p_utf8) {
return true;
@@ -1766,12 +1646,12 @@ bool String::parse_utf8(const char *p_utf8, int p_len) {
} else if ((c & 0xf8) == 0xf0) {
skip = 3;
} else {
- _UNICERROR("invalid skip at " + num_int64(cstr_size));
+ UNICERROR("invalid skip at " + num_int64(cstr_size));
return true; //invalid utf8
}
if (skip == 1 && (c & 0x1e) == 0) {
- _UNICERROR("overlong rejected at " + num_int64(cstr_size));
+ UNICERROR("overlong rejected at " + num_int64(cstr_size));
return true; //reject overlong
}
@@ -1786,7 +1666,7 @@ bool String::parse_utf8(const char *p_utf8, int p_len) {
}
if (skip) {
- _UNICERROR("no space left");
+ UNICERROR("no space left");
return true; //not enough space
}
}
@@ -1813,17 +1693,17 @@ bool String::parse_utf8(const char *p_utf8, int p_len) {
} else if ((*p_utf8 & 0xf8) == 0xf0) {
len = 4;
} else {
- _UNICERROR("invalid len");
+ UNICERROR("invalid len");
return true; //invalid UTF8
}
if (len > cstr_size) {
- _UNICERROR("no space left");
+ UNICERROR("no space left");
return true; //not enough space
}
if (len == 2 && (*p_utf8 & 0x1E) == 0) {
- _UNICERROR("no space left");
+ UNICERROR("no space left");
return true; //reject overlong
}
@@ -1838,18 +1718,18 @@ bool String::parse_utf8(const char *p_utf8, int p_len) {
for (int i = 1; i < len; i++) {
if ((p_utf8[i] & 0xc0) != 0x80) {
- _UNICERROR("invalid utf8");
+ UNICERROR("invalid utf8");
return true; //invalid utf8
}
if (unichar == 0 && i == 2 && ((p_utf8[i] & 0x7f) >> (7 - len)) == 0) {
- _UNICERROR("invalid utf8 overlong");
+ UNICERROR("invalid utf8 overlong");
return true; //no overlong
}
unichar = (unichar << 6) | (p_utf8[i] & 0x3f);
}
}
if (unichar >= 0xd800 && unichar <= 0xdfff) {
- _UNICERROR("invalid code point");
+ UNICERROR("invalid code point");
return CharString();
}
@@ -1859,7 +1739,7 @@ bool String::parse_utf8(const char *p_utf8, int p_len) {
}
return false;
-#undef _UNICERROR
+#undef UNICERROR
}
CharString String::utf8() const {
@@ -1933,7 +1813,7 @@ String String::utf16(const char16_t *p_utf16, int p_len) {
}
bool String::parse_utf16(const char16_t *p_utf16, int p_len) {
-#define _UNICERROR(m_err) print_error("Unicode parsing error: " + String(m_err) + ". Is the string valid UTF-16?");
+#define UNICERROR(m_err) print_error("Unicode parsing error: " + String(m_err) + ". Is the string valid UTF-16?");
if (!p_utf16) {
return true;
@@ -1973,7 +1853,7 @@ bool String::parse_utf16(const char16_t *p_utf16, int p_len) {
if ((c & 0xfffffc00) == 0xd800) {
skip = 1; // lead surrogate
} else if ((c & 0xfffffc00) == 0xdc00) {
- _UNICERROR("invalid utf16 surrogate at " + num_int64(cstr_size));
+ UNICERROR("invalid utf16 surrogate at " + num_int64(cstr_size));
return true; // invalid UTF16
} else {
skip = 0;
@@ -1983,7 +1863,7 @@ bool String::parse_utf16(const char16_t *p_utf16, int p_len) {
if ((c & 0xfffffc00) == 0xdc00) { // trail surrogate
--skip;
} else {
- _UNICERROR("invalid utf16 surrogate at " + num_int64(cstr_size));
+ UNICERROR("invalid utf16 surrogate at " + num_int64(cstr_size));
return true; // invalid UTF16
}
}
@@ -1993,7 +1873,7 @@ bool String::parse_utf16(const char16_t *p_utf16, int p_len) {
}
if (skip) {
- _UNICERROR("no space left");
+ UNICERROR("no space left");
return true; // not enough space
}
}
@@ -2018,7 +1898,7 @@ bool String::parse_utf16(const char16_t *p_utf16, int p_len) {
}
if (len > cstr_size) {
- _UNICERROR("no space left");
+ UNICERROR("no space left");
return true; //not enough space
}
@@ -2036,7 +1916,7 @@ bool String::parse_utf16(const char16_t *p_utf16, int p_len) {
}
return false;
-#undef _UNICERROR
+#undef UNICERROR
}
Char16String String::utf16() const {
@@ -2305,7 +2185,7 @@ bool String::is_numeric() const {
return false;
}
dot = true;
- } else if (c < '0' || c > '9') {
+ } else if (!is_digit(c)) {
return false;
}
}
@@ -3173,7 +3053,7 @@ bool String::is_subsequence_of(const String &p_string) const {
return _base_is_subsequence_of(p_string, false);
}
-bool String::is_subsequence_ofi(const String &p_string) const {
+bool String::is_subsequence_ofn(const String &p_string) const {
return _base_is_subsequence_of(p_string, true);
}
@@ -3509,6 +3389,27 @@ char32_t String::unicode_at(int p_idx) const {
return operator[](p_idx);
}
+String String::indent(const String &p_prefix) const {
+ String new_string;
+ int line_start = 0;
+
+ for (int i = 0; i < length(); i++) {
+ const char32_t c = operator[](i);
+ if (c == '\n') {
+ if (i == line_start) {
+ new_string += c; // Leave empty lines empty.
+ } else {
+ new_string += p_prefix + substr(line_start, i - line_start + 1);
+ }
+ line_start = i + 1;
+ }
+ }
+ if (line_start != length()) {
+ new_string += p_prefix + substr(line_start);
+ }
+ return new_string;
+}
+
String String::dedent() const {
String new_string;
String indent;
@@ -3630,6 +3531,10 @@ String String::rstrip(const String &p_chars) const {
return substr(0, end + 1);
}
+bool String::is_network_share_path() const {
+ return begins_with("//") || begins_with("\\\\");
+}
+
String String::simplify_path() const {
String s = *this;
String drive;
@@ -3642,6 +3547,9 @@ String String::simplify_path() const {
} else if (s.begins_with("user://")) {
drive = "user://";
s = s.substr(7, s.length());
+ } else if (is_network_share_path()) {
+ drive = s.substr(0, 2);
+ s = s.substr(2, s.length() - 2);
} else if (s.begins_with("/") || s.begins_with("\\")) {
drive = s.substr(0, 1);
s = s.substr(1, s.length() - 1);
@@ -3756,7 +3664,7 @@ bool String::is_valid_identifier() const {
}
}
- bool valid_char = is_digit(str[i]) || is_lower_case(str[i]) || is_upper_case(str[i]) || str[i] == '_';
+ bool valid_char = is_ascii_identifier_char(str[i]);
if (!valid_char) {
return false;
@@ -3781,7 +3689,7 @@ String String::uri_encode() const {
String res;
for (int i = 0; i < temp.length(); ++i) {
char ord = temp[i];
- if (ord == '.' || ord == '-' || ord == '_' || ord == '~' || is_lower_case(ord) || is_upper_case(ord) || is_digit(ord)) {
+ if (ord == '.' || ord == '-' || ord == '~' || is_ascii_identifier_char(ord)) {
res += ord;
} else {
char h_Val[3];
@@ -3803,9 +3711,9 @@ String String::uri_decode() const {
for (int i = 0; i < src.length(); ++i) {
if (src[i] == '%' && i + 2 < src.length()) {
char ord1 = src[i + 1];
- if (is_digit(ord1) || is_upper_case(ord1)) {
+ if (is_digit(ord1) || is_ascii_upper_case(ord1)) {
char ord2 = src[i + 2];
- if (is_digit(ord2) || is_upper_case(ord2)) {
+ if (is_digit(ord2) || is_ascii_upper_case(ord2)) {
char bytes[3] = { (char)ord1, (char)ord2, 0 };
res += (char)strtol(bytes, nullptr, 16);
i += 2;
@@ -3932,7 +3840,7 @@ static _FORCE_INLINE_ int _xml_unescape(const char32_t *p_src, int p_src_len, ch
for (int i = 2; i < p_src_len; i++) {
eat = i + 1;
char32_t ct = p_src[i];
- if (ct == ';' || ct < '0' || ct > '9') {
+ if (ct == ';' || !is_digit(ct)) {
break;
}
}
@@ -4062,7 +3970,7 @@ String String::pad_zeros(int p_digits) const {
int begin = 0;
- while (begin < end && (s[begin] < '0' || s[begin] > '9')) {
+ while (begin < end && !is_digit(s[begin])) {
begin++;
}
@@ -4107,7 +4015,7 @@ bool String::is_valid_int() const {
}
for (int i = from; i < len; i++) {
- if (operator[](i) < '0' || operator[](i) > '9') {
+ if (!is_digit(operator[](i))) {
return false; // no start with number plz
}
}
@@ -4285,7 +4193,7 @@ bool String::is_valid_filename() const {
return false;
}
- if (stripped == String()) {
+ if (stripped.is_empty()) {
return false;
}
@@ -4343,13 +4251,13 @@ bool String::is_relative_path() const {
String String::get_base_dir() const {
int end = 0;
- // url scheme style base
+ // URL scheme style base.
int basepos = find("://");
if (basepos != -1) {
end = basepos + 3;
}
- // windows top level directory base
+ // Windows top level directory base.
if (end == 0) {
basepos = find(":/");
if (basepos == -1) {
@@ -4360,7 +4268,24 @@ String String::get_base_dir() const {
}
}
- // unix root directory base
+ // Windows UNC network share path.
+ if (end == 0) {
+ if (is_network_share_path()) {
+ basepos = find("/", 2);
+ if (basepos == -1) {
+ basepos = find("\\", 2);
+ }
+ int servpos = find("/", basepos + 1);
+ if (servpos == -1) {
+ servpos = find("\\", basepos + 1);
+ }
+ if (servpos != -1) {
+ end = servpos + 1;
+ }
+ }
+ }
+
+ // Unix root directory base.
if (end == 0) {
if (begins_with("/")) {
end = 1;
@@ -4904,7 +4829,7 @@ String DTRN(const String &p_text, const String &p_text_plural, int p_n, const St
String RTR(const String &p_text, const String &p_context) {
if (TranslationServer::get_singleton()) {
String rtr = TranslationServer::get_singleton()->tool_translate(p_text, p_context);
- if (rtr == String() || rtr == p_text) {
+ if (rtr.is_empty() || rtr == p_text) {
return TranslationServer::get_singleton()->translate(p_text, p_context);
} else {
return rtr;
@@ -4917,7 +4842,7 @@ String RTR(const String &p_text, const String &p_context) {
String RTRN(const String &p_text, const String &p_text_plural, int p_n, const String &p_context) {
if (TranslationServer::get_singleton()) {
String rtr = TranslationServer::get_singleton()->tool_translate_plural(p_text, p_text_plural, p_n, p_context);
- if (rtr == String() || rtr == p_text || rtr == p_text_plural) {
+ if (rtr.is_empty() || rtr == p_text || rtr == p_text_plural) {
return TranslationServer::get_singleton()->translate_plural(p_text, p_text_plural, p_n, p_context);
} else {
return rtr;
diff --git a/core/string/ustring.h b/core/string/ustring.h
index f25c36f66c..1d302b65a7 100644
--- a/core/string/ustring.h
+++ b/core/string/ustring.h
@@ -5,8 +5,8 @@
/* GODOT ENGINE */
/* https://godotengine.org */
/*************************************************************************/
-/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur. */
-/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md). */
+/* Copyright (c) 2007-2022 Juan Linietsky, Ariel Manzur. */
+/* Copyright (c) 2014-2022 Godot Engine contributors (cf. AUTHORS.md). */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
@@ -32,6 +32,7 @@
#define USTRING_GODOT_H
// Note: Renamed to avoid conflict with ICU header with the same name.
+#include "core/string/char_utils.h"
#include "core/templates/cowdata.h"
#include "core/templates/vector.h"
#include "core/typedefs.h"
@@ -108,13 +109,10 @@ public:
_FORCE_INLINE_ Char16String() {}
_FORCE_INLINE_ Char16String(const Char16String &p_str) { _cowdata._ref(p_str._cowdata); }
- _FORCE_INLINE_ Char16String &operator=(const Char16String &p_str) {
- _cowdata._ref(p_str._cowdata);
- return *this;
- }
+ _FORCE_INLINE_ void operator=(const Char16String &p_str) { _cowdata._ref(p_str._cowdata); }
_FORCE_INLINE_ Char16String(const char16_t *p_cstr) { copy_from(p_cstr); }
- Char16String &operator=(const char16_t *p_cstr);
+ void operator=(const char16_t *p_cstr);
bool operator<(const Char16String &p_right) const;
Char16String &operator+=(char16_t p_char);
int length() const { return size() ? size() - 1 : 0; }
@@ -152,13 +150,10 @@ public:
_FORCE_INLINE_ CharString() {}
_FORCE_INLINE_ CharString(const CharString &p_str) { _cowdata._ref(p_str._cowdata); }
- _FORCE_INLINE_ CharString &operator=(const CharString &p_str) {
- _cowdata._ref(p_str._cowdata);
- return *this;
- }
+ _FORCE_INLINE_ void operator=(const CharString &p_str) { _cowdata._ref(p_str._cowdata); }
_FORCE_INLINE_ CharString(const char *p_cstr) { copy_from(p_cstr); }
- CharString &operator=(const char *p_cstr);
+ void operator=(const char *p_cstr);
bool operator<(const CharString &p_right) const;
CharString &operator+=(char p_char);
int length() const { return size() ? size() - 1 : 0; }
@@ -291,7 +286,7 @@ public:
bool ends_with(const String &p_string) const;
bool is_enclosed_in(const String &p_string) const;
bool is_subsequence_of(const String &p_string) const;
- bool is_subsequence_ofi(const String &p_string) const;
+ bool is_subsequence_ofn(const String &p_string) const;
bool is_quoted() const;
Vector<String> bigrams() const;
float similarity(const String &p_string) const;
@@ -362,6 +357,7 @@ public:
String left(int p_pos) const;
String right(int p_pos) const;
+ String indent(const String &p_prefix) const;
String dedent() const;
String strip_edges(bool left = true, bool right = true) const;
String strip_escapes() const;
@@ -399,6 +395,8 @@ public:
Vector<uint8_t> sha256_buffer() const;
_FORCE_INLINE_ bool is_empty() const { return length() == 0; }
+ _FORCE_INLINE_ bool contains(const char *p_str) const { return find(p_str) != -1; }
+ _FORCE_INLINE_ bool contains(const String &p_str) const { return find(p_str) != -1; }
// path functions
bool is_absolute_path() const;
@@ -410,6 +408,7 @@ public:
String get_file() const;
static String humanize_size(uint64_t p_size);
String simplify_path() const;
+ bool is_network_share_path() const;
String xml_escape(bool p_escape_quotes = false) const;
String xml_unescape() const;
@@ -442,11 +441,7 @@ public:
_FORCE_INLINE_ String() {}
_FORCE_INLINE_ String(const String &p_str) { _cowdata._ref(p_str._cowdata); }
-
- String &operator=(const String &p_str) {
- _cowdata._ref(p_str._cowdata);
- return *this;
- }
+ _FORCE_INLINE_ void operator=(const String &p_str) { _cowdata._ref(p_str._cowdata); }
Vector<uint8_t> to_ascii_buffer() const;
Vector<uint8_t> to_utf8_buffer() const;
@@ -539,7 +534,6 @@ String DTRN(const String &p_text, const String &p_text_plural, int p_n, const St
String RTR(const String &p_text, const String &p_context = "");
String RTRN(const String &p_text, const String &p_text_plural, int p_n, const String &p_context = "");
-bool is_symbol(char32_t c);
bool select_word(const String &p_s, int p_col, int &r_beg, int &r_end);
_FORCE_INLINE_ void sarray_add_str(Vector<String> &arr) {