Cleanup and move char functions to the `char_utils.h` header.

core/io/http_client_tcp.cpp

@@ -614,7 +614,7 @@ PackedByteArray HTTPClientTCP::read_response_body_chunk() {
 					for (int i = 0; i < chunk.size() - 2; i++) {
 						char c = chunk[i];
 						int v = 0;
-						if (c >= '0' && c <= '9') {
+						if (is_digit(c)) {
 							v = c - '0';
 						} else if (c >= 'a' && c <= 'f') {
 							v = c - 'a' + 10;

core/io/image.cpp

@@ -2056,7 +2056,7 @@ void Image::create(const char **p_xpm) {
 						for (int i = 0; i < 6; i++) {
 							char v = line_ptr[i];
 
-							if (v >= '0' && v <= '9') {
+							if (is_digit(v)) {
 								v -= '0';
 							} else if (v >= 'A' && v <= 'F') {
 								v = (v - 'A') + 10;

core/io/ip_address.cpp

@@ -71,7 +71,7 @@ static void _parse_hex(const String &p_string, int p_start, uint8_t *p_dst) {
 
 		int n = 0;
 		char32_t c = p_string[i];
-		if (c >= '0' && c <= '9') {
+		if (is_digit(c)) {
 			n = c - '0';
 		} else if (c >= 'a' && c <= 'f') {
 			n = 10 + (c - 'a');
@@ -113,7 +113,7 @@ void IPAddress::_parse_ipv6(const String &p_string) {
 		} else if (c == '.') {
 			part_ipv4 = true;
 
-		} else if ((c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F')) {
+		} else if (is_hex_digit(c)) {
 			if (!part_found) {
 				parts[parts_idx++] = i;
 				part_found = true;

core/io/json.cpp

@@ -229,12 +229,12 @@ Error JSON::_get_token(const char32_t *p_str, int &index, int p_len, Token &r_to
 										r_err_str = "Unterminated String";
 										return ERR_PARSE_ERROR;
 									}
-									if (!((c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'))) {
+									if (!is_hex_digit(c)) {
 										r_err_str = "Malformed hex constant in string";
 										return ERR_PARSE_ERROR;
 									}
 									char32_t v;
-									if (c >= '0' && c <= '9') {
+									if (is_digit(c)) {
 										v = c - '0';
 									} else if (c >= 'a' && c <= 'f') {
 										v = c - 'a';
@@ -265,12 +265,12 @@ Error JSON::_get_token(const char32_t *p_str, int &index, int p_len, Token &r_to
 											r_err_str = "Unterminated String";
 											return ERR_PARSE_ERROR;
 										}
-										if (!((c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'))) {
+										if (!is_hex_digit(c)) {
 											r_err_str = "Malformed hex constant in string";
 											return ERR_PARSE_ERROR;
 										}
 										char32_t v;
-										if (c >= '0' && c <= '9') {
+										if (is_digit(c)) {
 											v = c - '0';
 										} else if (c >= 'a' && c <= 'f') {
 											v = c - 'a';
@@ -326,7 +326,7 @@ Error JSON::_get_token(const char32_t *p_str, int &index, int p_len, Token &r_to
 					break;
 				}
 
-				if (p_str[index] == '-' || (p_str[index] >= '0' && p_str[index] <= '9')) {
+				if (p_str[index] == '-' || is_digit(p_str[index])) {
 					//a number
 					const char32_t *rptr;
 					double number = String::to_float(&p_str[index], &rptr);
@@ -335,10 +335,10 @@ Error JSON::_get_token(const char32_t *p_str, int &index, int p_len, Token &r_to
 					r_token.value = number;
 					return OK;
 
-				} else if ((p_str[index] >= 'A' && p_str[index] <= 'Z') || (p_str[index] >= 'a' && p_str[index] <= 'z')) {
+				} else if (is_ascii_char(p_str[index])) {
 					String id;
 
-					while ((p_str[index] >= 'A' && p_str[index] <= 'Z') || (p_str[index] >= 'a' && p_str[index] <= 'z')) {
+					while (is_ascii_char(p_str[index])) {
 						id += p_str[index];
 						index++;
 					}

core/io/pck_packer.cpp

@@ -62,7 +62,7 @@ Error PCKPacker::pck_start(const String &p_file, int p_alignment, const String &
 		int v = 0;
 		if (i * 2 < _key.length()) {
 			char32_t ct = _key[i * 2];
-			if (ct >= '0' && ct <= '9') {
+			if (is_digit(ct)) {
 				ct = ct - '0';
 			} else if (ct >= 'a' && ct <= 'f') {
 				ct = 10 + ct - 'a';
@@ -72,7 +72,7 @@ Error PCKPacker::pck_start(const String &p_file, int p_alignment, const String &
 
 		if (i * 2 + 1 < _key.length()) {
 			char32_t ct = _key[i * 2 + 1];
-			if (ct >= '0' && ct <= '9') {
+			if (is_digit(ct)) {
 				ct = ct - '0';
 			} else if (ct >= 'a' && ct <= 'f') {
 				ct = 10 + ct - 'a';

core/io/resource_uid.cpp

@@ -71,9 +71,9 @@ ResourceUID::ID ResourceUID::text_to_id(const String &p_text) const {
 	for (uint32_t i = 6; i < l; i++) {
 		uid *= base;
 		uint32_t c = p_text[i];
-		if (c >= 'a' && c <= 'z') {
+		if (is_ascii_lower_case(c)) {
 			uid += c - 'a';
-		} else if (c >= '0' && c <= '9') {
+		} else if (is_digit(c)) {
 			uid += c - '0' + char_count;
 		} else {
 			return INVALID_ID;

core/math/expression.cpp

@@ -37,18 +37,6 @@
 #include "core/os/os.h"
 #include "core/variant/variant_parser.h"
 
-static bool _is_number(char32_t c) {
-	return (c >= '0' && c <= '9');
-}
-
-static bool _is_hex_digit(char32_t c) {
-	return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F');
-}
-
-static bool _is_binary_digit(char32_t c) {
-	return (c == '0' || c == '1');
-}
-
 Error Expression::_get_token(Token &r_token) {
 	while (true) {
 #define GET_CHAR() (str_ofs >= expression.length() ? 0 : expression[str_ofs++])
@@ -96,7 +84,7 @@ Error Expression::_get_token(Token &r_token) {
 				r_token.type = TK_INPUT;
 				int index = 0;
 				do {
-					if (!_is_number(expression[str_ofs])) {
+					if (!is_digit(expression[str_ofs])) {
 						_set_error("Expected number after '$'");
 						r_token.type = TK_ERROR;
 						return ERR_PARSE_ERROR;
@@ -105,7 +93,7 @@ Error Expression::_get_token(Token &r_token) {
 					index += expression[str_ofs] - '0';
 					str_ofs++;
 
-				} while (_is_number(expression[str_ofs]));
+				} while (is_digit(expression[str_ofs]));
 
 				r_token.value = index;
 				return OK;
@@ -255,13 +243,13 @@ Error Expression::_get_token(Token &r_token) {
 										r_token.type = TK_ERROR;
 										return ERR_PARSE_ERROR;
 									}
-									if (!(_is_number(c) || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'))) {
+									if (!is_hex_digit(c)) {
 										_set_error("Malformed hex constant in string");
 										r_token.type = TK_ERROR;
 										return ERR_PARSE_ERROR;
 									}
 									char32_t v;
-									if (_is_number(c)) {
+									if (is_digit(c)) {
 										v = c - '0';
 									} else if (c >= 'a' && c <= 'f') {
 										v = c - 'a';
@@ -336,7 +324,7 @@ Error Expression::_get_token(Token &r_token) {
 				}
 
 				char32_t next_char = (str_ofs >= expression.length()) ? 0 : expression[str_ofs];
-				if (_is_number(cchar) || (cchar == '.' && _is_number(next_char))) {
+				if (is_digit(cchar) || (cchar == '.' && is_digit(next_char))) {
 					//a number
 
 					String num;
@@ -360,7 +348,7 @@ Error Expression::_get_token(Token &r_token) {
 					while (true) {
 						switch (reading) {
 							case READING_INT: {
-								if (_is_number(c)) {
+								if (is_digit(c)) {
 									if (is_first_char && c == '0') {
 										if (next_char == 'b') {
 											reading = READING_BIN;
@@ -379,7 +367,7 @@ Error Expression::_get_token(Token &r_token) {
 
 							} break;
 							case READING_BIN: {
-								if (bin_beg && !_is_binary_digit(c)) {
+								if (bin_beg && !is_binary_digit(c)) {
 									reading = READING_DONE;
 								} else if (c == 'b') {
 									bin_beg = true;
@@ -387,7 +375,7 @@ Error Expression::_get_token(Token &r_token) {
 
 							} break;
 							case READING_HEX: {
-								if (hex_beg && !_is_hex_digit(c)) {
+								if (hex_beg && !is_hex_digit(c)) {
 									reading = READING_DONE;
 								} else if (c == 'x') {
 									hex_beg = true;
@@ -395,7 +383,7 @@ Error Expression::_get_token(Token &r_token) {
 
 							} break;
 							case READING_DEC: {
-								if (_is_number(c)) {
+								if (is_digit(c)) {
 								} else if (c == 'e') {
 									reading = READING_EXP;
 
@@ -405,7 +393,7 @@ Error Expression::_get_token(Token &r_token) {
 
 							} break;
 							case READING_EXP: {
-								if (_is_number(c)) {
+								if (is_digit(c)) {
 									exp_beg = true;
 
 								} else if ((c == '-' || c == '+') && !exp_sign && !exp_beg) {
@@ -443,11 +431,11 @@ Error Expression::_get_token(Token &r_token) {
 					}
 					return OK;
 
-				} else if ((cchar >= 'A' && cchar <= 'Z') || (cchar >= 'a' && cchar <= 'z') || cchar == '_') {
+				} else if (is_ascii_char(cchar) || is_underscore(cchar)) {
 					String id;
 					bool first = true;
 
-					while ((cchar >= 'A' && cchar <= 'Z') || (cchar >= 'a' && cchar <= 'z') || cchar == '_' || (!first && _is_number(cchar))) {
+					while (is_ascii_char(cchar) || is_underscore(cchar) || (!first && is_digit(cchar))) {
 						id += String::chr(cchar);
 						cchar = GET_CHAR();
 						first = false;

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

core/string/translation.cpp

@@ -213,14 +213,6 @@ static _character_accent_pair _character_to_accented[] = {
 	{ 'z', U"ź" },
 };
 
-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');
-}
-
 Vector<TranslationServer::LocaleScriptInfo> TranslationServer::locale_script_info;
 
 Map<String, String> TranslationServer::language_map;
@@ -309,15 +301,15 @@ String TranslationServer::standardize_locale(const String &p_locale) const {
 	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_upper_case(locale_elements[1][0]) && is_lower_case(locale_elements[1][1]) && is_lower_case(locale_elements[1][2]) && is_lower_case(locale_elements[1][3])) {
+		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_upper_case(locale_elements[1][0]) && is_upper_case(locale_elements[1][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_upper_case(locale_elements[2][0]) && is_upper_case(locale_elements[2][1])) {
+		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();
@@ -434,15 +426,15 @@ String TranslationServer::get_locale_name(const String &p_locale) const {
 	Vector<String> locale_elements = locale.split("_");
 	lang = locale_elements[0];
 	if (locale_elements.size() >= 2) {
-		if (locale_elements[1].length() == 4 && is_upper_case(locale_elements[1][0]) && is_lower_case(locale_elements[1][1]) && is_lower_case(locale_elements[1][2]) && is_lower_case(locale_elements[1][3])) {
+		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_upper_case(locale_elements[1][0]) && is_upper_case(locale_elements[1][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_upper_case(locale_elements[2][0]) && is_upper_case(locale_elements[2][1])) {
+		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];
 		}
 	}
@@ -911,7 +903,7 @@ 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;
 	}
 

core/string/ustring.cpp

@@ -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());
@@ -974,21 +954,21 @@ 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]);
 		}
 
@@ -2212,7 +2192,7 @@ bool String::is_numeric() const {
 				return false;
 			}
 			dot = true;
-		} else if (c < '0' || c > '9') {
+		} else if (!is_digit(c)) {
 			return false;
 		}
 	}
@@ -3691,7 +3671,7 @@ 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;
@@ -3716,7 +3696,7 @@ 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];
@@ -3738,9 +3718,9 @@ 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;
@@ -3867,7 +3847,7 @@ 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;
 						}
 					}
@@ -3997,7 +3977,7 @@ 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++;
 	}
 
@@ -4042,7 +4022,7 @@ 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
 		}
 	}

core/string/ustring.h

@@ -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"
@@ -533,7 +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) {

core/variant/variant_parser.cpp

@@ -188,7 +188,7 @@ Error VariantParser::get_token(Stream *p_stream, Token &r_token, int &line, Stri
 					if (p_stream->is_eof()) {
 						r_token.type = TK_EOF;
 						return OK;
-					} else if ((ch >= '0' && ch <= '9') || (ch >= 'a' && ch <= 'f') || (ch >= 'A' && ch <= 'F')) {
+					} else if (is_hex_digit(ch)) {
 						color_str += ch;
 
 					} else {
@@ -265,13 +265,13 @@ Error VariantParser::get_token(Stream *p_stream, Token &r_token, int &line, Stri
 										r_token.type = TK_ERROR;
 										return ERR_PARSE_ERROR;
 									}
-									if (!((c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'))) {
+									if (!is_hex_digit(c)) {
 										r_err_str = "Malformed hex constant in string";
 										r_token.type = TK_ERROR;
 										return ERR_PARSE_ERROR;
 									}
 									char32_t v;
-									if (c >= '0' && c <= '9') {
+									if (is_digit(c)) {
 										v = c - '0';
 									} else if (c >= 'a' && c <= 'f') {
 										v = c - 'a';
@@ -381,7 +381,7 @@ Error VariantParser::get_token(Stream *p_stream, Token &r_token, int &line, Stri
 					while (true) {
 						switch (reading) {
 							case READING_INT: {
-								if (c >= '0' && c <= '9') {
+								if (is_digit(c)) {
 									//pass
 								} else if (c == '.') {
 									reading = READING_DEC;
@@ -395,7 +395,7 @@ Error VariantParser::get_token(Stream *p_stream, Token &r_token, int &line, Stri
 
 							} break;
 							case READING_DEC: {
-								if (c >= '0' && c <= '9') {
+								if (is_digit(c)) {
 								} else if (c == 'e') {
 									reading = READING_EXP;
 								} else {
@@ -404,7 +404,7 @@ Error VariantParser::get_token(Stream *p_stream, Token &r_token, int &line, Stri
 
 							} break;
 							case READING_EXP: {
-								if (c >= '0' && c <= '9') {
+								if (is_digit(c)) {
 									exp_beg = true;
 
 								} else if ((c == '-' || c == '+') && !exp_sign && !exp_beg) {
@@ -433,11 +433,11 @@ Error VariantParser::get_token(Stream *p_stream, Token &r_token, int &line, Stri
 						r_token.value = num.as_int();
 					}
 					return OK;
-				} else if ((cchar >= 'A' && cchar <= 'Z') || (cchar >= 'a' && cchar <= 'z') || cchar == '_') {
+				} else if (is_ascii_char(cchar) || is_underscore(cchar)) {
 					StringBuffer<> id;
 					bool first = true;
 
-					while ((cchar >= 'A' && cchar <= 'Z') || (cchar >= 'a' && cchar <= 'z') || cchar == '_' || (!first && cchar >= '0' && cchar <= '9')) {
+					while (is_ascii_char(cchar) || is_underscore(cchar) || (!first && is_digit(cchar))) {
 						id += cchar;
 						cchar = p_stream->get_char();
 						first = false;

editor/connections_dialog.cpp

@@ -764,7 +764,7 @@ void ConnectionsDock::_open_connection_dialog(TreeItem &p_item) {
 	String node_name = selected_node->get_name();
 	for (int i = 0; i < node_name.length(); i++) { // TODO: Regex filter may be cleaner.
 		char32_t c = node_name[i];
-		if (!((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_')) {
+		if (!is_ascii_identifier_char(c)) {
 			if (c == ' ') {
 				// Replace spaces with underlines.
 				c = '_';

editor/editor_export.cpp

@@ -818,7 +818,7 @@ Error EditorExportPlatform::export_project_files(const Ref<EditorExportPreset> &
 				int v = 0;
 				if (i * 2 < script_key.length()) {
 					char32_t ct = script_key[i * 2];
-					if (ct >= '0' && ct <= '9') {
+					if (is_digit(ct)) {
 						ct = ct - '0';
 					} else if (ct >= 'a' && ct <= 'f') {
 						ct = 10 + ct - 'a';
@@ -828,7 +828,7 @@ Error EditorExportPlatform::export_project_files(const Ref<EditorExportPreset> &
 
 				if (i * 2 + 1 < script_key.length()) {
 					char32_t ct = script_key[i * 2 + 1];
-					if (ct >= '0' && ct <= '9') {
+					if (is_digit(ct)) {
 						ct = ct - '0';
 					} else if (ct >= 'a' && ct <= 'f') {
 						ct = 10 + ct - 'a';
@@ -1215,7 +1215,7 @@ Error EditorExportPlatform::save_pack(const Ref<EditorExportPreset> &p_preset, c
 				int v = 0;
 				if (i * 2 < script_key.length()) {
 					char32_t ct = script_key[i * 2];
-					if (ct >= '0' && ct <= '9') {
+					if (is_digit(ct)) {
 						ct = ct - '0';
 					} else if (ct >= 'a' && ct <= 'f') {
 						ct = 10 + ct - 'a';
@@ -1225,7 +1225,7 @@ Error EditorExportPlatform::save_pack(const Ref<EditorExportPreset> &p_preset, c
 
 				if (i * 2 + 1 < script_key.length()) {
 					char32_t ct = script_key[i * 2 + 1];
-					if (ct >= '0' && ct <= '9') {
+					if (is_digit(ct)) {
 						ct = ct - '0';
 					} else if (ct >= 'a' && ct <= 'f') {
 						ct = 10 + ct - 'a';

editor/editor_inspector.cpp

@@ -1780,7 +1780,7 @@ Array EditorInspectorArray::_extract_properties_as_array(const List<PropertyInfo
 
 			int to_char_index = 0;
 			while (to_char_index < str.length()) {
-				if (str[to_char_index] < '0' || str[to_char_index] > '9') {
+				if (!is_digit(str[to_char_index])) {
 					break;
 				}
 				to_char_index++;
@@ -2512,7 +2512,7 @@ void EditorInspector::update_tree() {
 			String str = p.name.trim_prefix(array_prefix);
 			int to_char_index = 0;
 			while (to_char_index < str.length()) {
-				if (str[to_char_index] < '0' || str[to_char_index] > '9') {
+				if (!is_digit(str[to_char_index])) {
 					break;
 				}
 				to_char_index++;

editor/editor_locale_dialog.cpp

@@ -37,14 +37,6 @@
 #include "scene/gui/option_button.h"
 #include "scene/gui/tree.h"
 
-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');
-}
-
 void EditorLocaleDialog::_bind_methods() {
 	ADD_SIGNAL(MethodInfo("locale_selected", PropertyInfo(Variant::STRING, "locale")));
 }
@@ -363,16 +355,16 @@ void EditorLocaleDialog::set_locale(const String &p_locale) {
 		Vector<String> locale_elements = p_locale.split("_");
 		lang_code->set_text(locale_elements[0]);
 		if (locale_elements.size() >= 2) {
-			if (locale_elements[1].length() == 4 && is_upper_case(locale_elements[1][0]) && is_lower_case(locale_elements[1][1]) && is_lower_case(locale_elements[1][2]) && is_lower_case(locale_elements[1][3])) {
+			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_code->set_text(locale_elements[1]);
 				advanced->set_pressed(true);
 			}
-			if (locale_elements[1].length() == 2 && is_upper_case(locale_elements[1][0]) && is_upper_case(locale_elements[1][1])) {
+			if (locale_elements[1].length() == 2 && is_ascii_upper_case(locale_elements[1][0]) && is_ascii_upper_case(locale_elements[1][1])) {
 				country_code->set_text(locale_elements[1]);
 			}
 		}
 		if (locale_elements.size() >= 3) {
-			if (locale_elements[2].length() == 2 && is_upper_case(locale_elements[2][0]) && is_upper_case(locale_elements[2][1])) {
+			if (locale_elements[2].length() == 2 && is_ascii_upper_case(locale_elements[2][0]) && is_ascii_upper_case(locale_elements[2][1])) {
 				country_code->set_text(locale_elements[2]);
 			} else {
 				variant_code->set_text(locale_elements[2].to_lower());

editor/find_in_files.cpp

@@ -53,11 +53,6 @@ inline void pop_back(T &container) {
 	container.resize(container.size() - 1);
 }
 
-// TODO: Copied from TextEdit private, would be nice to extract it in a single place.
-static bool is_text_char(char32_t c) {
-	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_';
-}
-
 static bool find_next(const String &line, String pattern, int from, bool match_case, bool whole_words, int &out_begin, int &out_end) {
 	int end = from;
 
@@ -73,10 +68,10 @@ static bool find_next(const String &line, String pattern, int from, bool match_c
 		out_end = end;
 
 		if (whole_words) {
-			if (begin > 0 && is_text_char(line[begin - 1])) {
+			if (begin > 0 && (is_ascii_identifier_char(line[begin - 1]))) {
 				continue;
 			}
-			if (end < line.size() && is_text_char(line[end])) {
+			if (end < line.size() && (is_ascii_identifier_char(line[end]))) {
 				continue;
 			}
 		}

editor/import/resource_importer_scene.cpp

@@ -316,7 +316,7 @@ static bool _teststr(const String &p_what, const String &p_str) {
 	String what = p_what;
 
 	//remove trailing spaces and numbers, some apps like blender add ".number" to duplicates so also compensate for this
-	while (what.length() && ((what[what.length() - 1] >= '0' && what[what.length() - 1] <= '9') || what[what.length() - 1] <= 32 || what[what.length() - 1] == '.')) {
+	while (what.length() && (is_digit(what[what.length() - 1]) || what[what.length() - 1] <= 32 || what[what.length() - 1] == '.')) {
 		what = what.substr(0, what.length() - 1);
 	}
 
@@ -336,7 +336,7 @@ static String _fixstr(const String &p_what, const String &p_str) {
 	String what = p_what;
 
 	//remove trailing spaces and numbers, some apps like blender add ".number" to duplicates so also compensate for this
-	while (what.length() && ((what[what.length() - 1] >= '0' && what[what.length() - 1] <= '9') || what[what.length() - 1] <= 32 || what[what.length() - 1] == '.')) {
+	while (what.length() && (is_digit(what[what.length() - 1]) || what[what.length() - 1] <= 32 || what[what.length() - 1] == '.')) {
 		what = what.substr(0, what.length() - 1);
 	}
 

editor/plugins/editor_preview_plugins.cpp

@@ -462,10 +462,6 @@ EditorMaterialPreviewPlugin::~EditorMaterialPreviewPlugin() {
 
 ///////////////////////////////////////////////////////////////////////////
 
-static bool _is_text_char(char32_t c) {
-	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_';
-}
-
 bool EditorScriptPreviewPlugin::handles(const String &p_type) const {
 	return ClassDB::is_parent_class(p_type, "Script");
 }
@@ -538,15 +534,15 @@ Ref<Texture2D> EditorScriptPreviewPlugin::generate(const RES &p_from, const Size
 				if (in_comment) {
 					color = comment_color;
 				} else {
-					if (c != '_' && ((c >= '!' && c <= '/') || (c >= ':' && c <= '@') || (c >= '[' && c <= '`') || (c >= '{' && c <= '~') || c == '\t')) {
+					if (is_symbol(c)) {
 						//make symbol a little visible
 						color = symbol_color;
 						in_control_flow_keyword = false;
 						in_keyword = false;
-					} else if (!prev_is_text && _is_text_char(c)) {
+					} else if (!prev_is_text && is_ascii_identifier_char(c)) {
 						int pos = i;
 
-						while (_is_text_char(code[pos])) {
+						while (is_ascii_identifier_char(code[pos])) {
 							pos++;
 						}
 						String word = code.substr(i, pos - i);
@@ -556,7 +552,7 @@ Ref<Texture2D> EditorScriptPreviewPlugin::generate(const RES &p_from, const Size
 							in_keyword = true;
 						}
 
-					} else if (!_is_text_char(c)) {
+					} else if (!is_ascii_identifier_char(c)) {
 						in_keyword = false;
 					}
 
@@ -571,7 +567,7 @@ Ref<Texture2D> EditorScriptPreviewPlugin::generate(const RES &p_from, const Size
 				img->set_pixel(col, y0 + line * 2, bg_color.blend(ul));
 				img->set_pixel(col, y0 + line * 2 + 1, color);
 
-				prev_is_text = _is_text_char(c);
+				prev_is_text = is_ascii_identifier_char(c);
 			}
 			col++;
 		} else {

editor/plugins/tiles/tile_map_editor.cpp

@@ -3735,7 +3735,7 @@ void TileMapEditor::_move_tile_map_array_element(Object *p_undo_redo, Object *p_
 			String str = pi.name.trim_prefix(p_array_prefix);
 			int to_char_index = 0;
 			while (to_char_index < str.length()) {
-				if (str[to_char_index] < '0' || str[to_char_index] > '9') {
+				if (!is_digit(str[to_char_index])) {
 					break;
 				}
 				to_char_index++;

editor/plugins/tiles/tile_set_editor.cpp

@@ -458,7 +458,7 @@ void TileSetEditor::_move_tile_set_array_element(Object *p_undo_redo, Object *p_
 			String str = pi.name.trim_prefix(p_array_prefix);
 			int to_char_index = 0;
 			while (to_char_index < str.length()) {
-				if (str[to_char_index] < '0' || str[to_char_index] > '9') {
+				if (!is_digit(str[to_char_index])) {
 					break;
 				}
 				to_char_index++;

editor/script_create_dialog.cpp

@@ -153,7 +153,7 @@ bool ScriptCreateDialog::_validate_class(const String &p_string) {
 			}
 		}
 
-		bool valid_char = (p_string[i] >= '0' && p_string[i] <= '9') || (p_string[i] >= 'a' && p_string[i] <= 'z') || (p_string[i] >= 'A' && p_string[i] <= 'Z') || p_string[i] == '_' || p_string[i] == '.';
+		bool valid_char = is_ascii_identifier_char(p_string[i]) || p_string[i] == '.';
 
 		if (!valid_char) {
 			return false;

modules/gdscript/editor/gdscript_highlighter.cpp

@@ -33,18 +33,6 @@
 #include "../gdscript_tokenizer.h"
 #include "editor/editor_settings.h"
 
-static bool _is_char(char32_t c) {
-	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || c == '_';
-}
-
-static bool _is_hex_symbol(char32_t c) {
-	return ((c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'));
-}
-
-static bool _is_bin_symbol(char32_t c) {
-	return (c == '0' || c == '1');
-}
-
 Dictionary GDScriptSyntaxHighlighter::_get_line_syntax_highlighting_impl(int p_line) {
 	Dictionary color_map;
 
@@ -102,7 +90,7 @@ Dictionary GDScriptSyntaxHighlighter::_get_line_syntax_highlighting_impl(int p_l
 		color = font_color;
 		bool is_char = !is_symbol(str[j]);
 		bool is_a_symbol = is_symbol(str[j]);
-		bool is_number = (str[j] >= '0' && str[j] <= '9');
+		bool is_number = is_digit(str[j]);
 
 		/* color regions */
 		if (is_a_symbol || in_region != -1) {
@@ -241,14 +229,14 @@ Dictionary GDScriptSyntaxHighlighter::_get_line_syntax_highlighting_impl(int p_l
 		}
 
 		// allow ABCDEF in hex notation
-		if (is_hex_notation && (_is_hex_symbol(str[j]) || is_number)) {
+		if (is_hex_notation && (is_hex_digit(str[j]) || is_number)) {
 			is_number = true;
 		} else {
 			is_hex_notation = false;
 		}
 
 		// disallow anything not a 0 or 1
-		if (is_bin_notation && (_is_bin_symbol(str[j]))) {
+		if (is_bin_notation && (is_binary_digit(str[j]))) {
 			is_number = true;
 		} else if (is_bin_notation) {
 			is_bin_notation = false;
@@ -270,7 +258,7 @@ Dictionary GDScriptSyntaxHighlighter::_get_line_syntax_highlighting_impl(int p_l
 			}
 		}
 
-		if (!in_word && _is_char(str[j]) && !is_number) {
+		if (!in_word && (is_ascii_char(str[j]) || is_underscore(str[j])) && !is_number) {
 			in_word = true;
 		}
 

modules/gdscript/gdscript_tokenizer.cpp

@@ -312,22 +312,6 @@ GDScriptTokenizer::Token GDScriptTokenizer::pop_error() {
 	return error;
 }
 
-static bool _is_alphanumeric(char32_t c) {
-	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_';
-}
-
-static bool _is_digit(char32_t c) {
-	return (c >= '0' && c <= '9');
-}
-
-static bool _is_hex_digit(char32_t c) {
-	return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F');
-}
-
-static bool _is_binary_digit(char32_t c) {
-	return (c == '0' || c == '1');
-}
-
 GDScriptTokenizer::Token GDScriptTokenizer::make_token(Token::Type p_type) {
 	Token token(p_type);
 	token.start_line = start_line;
@@ -448,10 +432,10 @@ GDScriptTokenizer::Token GDScriptTokenizer::check_vcs_marker(char32_t p_test, To
 }
 
 GDScriptTokenizer::Token GDScriptTokenizer::annotation() {
-	if (!_is_alphanumeric(_peek())) {
+	if (!is_ascii_identifier_char(_peek())) {
 		push_error("Expected annotation identifier after \"@\".");
 	}
-	while (_is_alphanumeric(_peek())) {
+	while (is_ascii_identifier_char(_peek())) {
 		// Consume all identifier characters.
 		_advance();
 	}
@@ -526,7 +510,7 @@ GDScriptTokenizer::Token GDScriptTokenizer::potential_identifier() {
 #define MAX_KEYWORD_LENGTH 10
 
 	// Consume all alphanumeric characters.
-	while (_is_alphanumeric(_peek())) {
+	while (is_ascii_identifier_char(_peek())) {
 		_advance();
 	}
 
@@ -612,7 +596,7 @@ GDScriptTokenizer::Token GDScriptTokenizer::number() {
 	bool has_decimal = false;
 	bool has_exponent = false;
 	bool has_error = false;
-	bool (*digit_check_func)(char32_t) = _is_digit;
+	bool (*digit_check_func)(char32_t) = is_digit;
 
 	if (_peek(-1) == '.') {
 		has_decimal = true;
@@ -620,20 +604,20 @@ GDScriptTokenizer::Token GDScriptTokenizer::number() {
 		if (_peek() == 'x') {
 			// Hexadecimal.
 			base = 16;
-			digit_check_func = _is_hex_digit;
+			digit_check_func = is_hex_digit;
 			_advance();
 		} else if (_peek() == 'b') {
 			// Binary.
 			base = 2;
-			digit_check_func = _is_binary_digit;
+			digit_check_func = is_binary_digit;
 			_advance();
 		}
 	}
 
 	// Allow '_' to be used in a number, for readability.
 	bool previous_was_underscore = false;
-	while (digit_check_func(_peek()) || _peek() == '_') {
-		if (_peek() == '_') {
+	while (digit_check_func(_peek()) || is_underscore(_peek())) {
+		if (is_underscore(_peek())) {
 			if (previous_was_underscore) {
 				Token error = make_error(R"(Only one underscore can be used as a numeric separator.)");
 				error.start_column = column;
@@ -682,7 +666,7 @@ GDScriptTokenizer::Token GDScriptTokenizer::number() {
 			_advance();
 
 			// Consume decimal digits.
-			while (_is_digit(_peek()) || _peek() == '_') {
+			while (is_digit(_peek()) || is_underscore(_peek())) {
 				_advance();
 			}
 		}
@@ -696,7 +680,7 @@ GDScriptTokenizer::Token GDScriptTokenizer::number() {
 				_advance();
 			}
 			// Consume exponent digits.
-			if (!_is_digit(_peek())) {
+			if (!is_digit(_peek())) {
 				Token error = make_error(R"(Expected exponent value after "e".)");
 				error.start_column = column;
 				error.leftmost_column = column;
@@ -705,8 +689,8 @@ GDScriptTokenizer::Token GDScriptTokenizer::number() {
 				push_error(error);
 			}
 			previous_was_underscore = false;
-			while (_is_digit(_peek()) || _peek() == '_') {
-				if (_peek() == '_') {
+			while (is_digit(_peek()) || is_underscore(_peek())) {
+				if (is_underscore(_peek())) {
 					if (previous_was_underscore) {
 						Token error = make_error(R"(Only one underscore can be used as a numeric separator.)");
 						error.start_column = column;
@@ -733,7 +717,7 @@ GDScriptTokenizer::Token GDScriptTokenizer::number() {
 		error.rightmost_column = column + 1;
 		push_error(error);
 		has_error = true;
-	} else if (_is_alphanumeric(_peek())) {
+	} else if (is_ascii_identifier_char(_peek())) {
 		// Letter at the end of the number.
 		push_error("Invalid numeric notation.");
 	}
@@ -865,7 +849,7 @@ GDScriptTokenizer::Token GDScriptTokenizer::string() {
 
 						char32_t digit = _peek();
 						char32_t value = 0;
-						if (digit >= '0' && digit <= '9') {
+						if (is_digit(digit)) {
 							value = digit - '0';
 						} else if (digit >= 'a' && digit <= 'f') {
 							value = digit - 'a';
@@ -1322,9 +1306,9 @@ GDScriptTokenizer::Token GDScriptTokenizer::scan() {
 
 	line_continuation = false;
 
-	if (_is_digit(c)) {
+	if (is_digit(c)) {
 		return number();
-	} else if (_is_alphanumeric(c)) {
+	} else if (is_ascii_identifier_char(c)) {
 		return potential_identifier();
 	}
 
@@ -1392,7 +1376,7 @@ GDScriptTokenizer::Token GDScriptTokenizer::scan() {
 			if (_peek() == '.') {
 				_advance();
 				return make_token(Token::PERIOD_PERIOD);
-			} else if (_is_digit(_peek())) {
+			} else if (is_digit(_peek())) {
 				// Number starting with '.'.
 				return number();
 			} else {

modules/gdscript/language_server/gdscript_extend_parser.cpp

@@ -541,7 +541,7 @@ String ExtendGDScriptParser::get_identifier_under_position(const lsp::Position &
 	for (int c = p_position.character; c >= 0; c--) {
 		start_pos = c;
 		char32_t ch = line[c];
-		bool valid_char = (ch >= '0' && ch <= '9') || (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || ch == '_';
+		bool valid_char = is_ascii_identifier_char(ch);
 		if (!valid_char) {
 			break;
 		}
@@ -550,7 +550,7 @@ String ExtendGDScriptParser::get_identifier_under_position(const lsp::Position &
 	int end_pos = p_position.character;
 	for (int c = p_position.character; c < line.length(); c++) {
 		char32_t ch = line[c];
-		bool valid_char = (ch >= '0' && ch <= '9') || (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || ch == '_';
+		bool valid_char = is_ascii_identifier_char(ch);
 		if (!valid_char) {
 			break;
 		}

modules/mono/editor/bindings_generator.cpp

@@ -690,11 +690,11 @@ void BindingsGenerator::_apply_prefix_to_enum_constants(BindingsGenerator::EnumI
 				continue;
 			}
 
-			if (parts[curr_prefix_length][0] >= '0' && parts[curr_prefix_length][0] <= '9') {
+			if (is_digit(parts[curr_prefix_length][0])) {
 				// The name of enum constants may begin with a numeric digit when strip from the enum prefix,
 				// so we make the prefix for this constant one word shorter in those cases.
 				for (curr_prefix_length = curr_prefix_length - 1; curr_prefix_length > 0; curr_prefix_length--) {
-					if (parts[curr_prefix_length][0] < '0' || parts[curr_prefix_length][0] > '9') {
+					if (!is_digit(parts[curr_prefix_length][0])) {
 						break;
 					}
 				}

modules/text_server_adv/text_server_adv.cpp

@@ -303,22 +303,6 @@ _FORCE_INLINE_ bool is_connected_to_prev(char32_t p_chr, char32_t p_pchr) {
 	return (prop != U_JT_RIGHT_JOINING) && (prop != U_JT_NON_JOINING) ? !is_ligature(p_pchr, p_chr) : false;
 }
 
-_FORCE_INLINE_ bool is_control(char32_t p_char) {
-	return (p_char <= 0x001f) || (p_char >= 0x007f && p_char <= 0x009F);
-}
-
-_FORCE_INLINE_ bool is_whitespace(char32_t p_char) {
-	return (p_char == 0x0020) || (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);
-}
-
-_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);
-}
-
-_FORCE_INLINE_ bool is_underscore(char32_t p_char) {
-	return (p_char == 0x005F);
-}
-
 /*************************************************************************/
 
 String TextServerAdvanced::interface_name = "ICU / HarfBuzz / Graphite";

modules/text_server_fb/text_server_fb.cpp

@@ -43,30 +43,6 @@
 #include "msdfgen.h"
 #endif
 
-/*************************************************************************/
-/*  Character properties.                                                */
-/*************************************************************************/
-
-_FORCE_INLINE_ bool is_control(char32_t p_char) {
-	return (p_char <= 0x001f) || (p_char >= 0x007f && p_char <= 0x009F);
-}
-
-_FORCE_INLINE_ bool is_whitespace(char32_t p_char) {
-	return (p_char == 0x0020) || (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);
-}
-
-_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);
-}
-
-_FORCE_INLINE_ bool is_punct(char32_t p_char) {
-	return (p_char >= 0x0020 && p_char <= 0x002F) || (p_char >= 0x003A && p_char <= 0x0040) || (p_char >= 0x005B && p_char <= 0x005E) || (p_char == 0x0060) || (p_char >= 0x007B && p_char <= 0x007E) || (p_char >= 0x2000 && p_char <= 0x206F) || (p_char >= 0x3000 && p_char <= 0x303F);
-}
-
-_FORCE_INLINE_ bool is_underscore(char32_t p_char) {
-	return (p_char == 0x005F);
-}
-
 /*************************************************************************/
 
 String TextServerFallback::interface_name = "Fallback";

modules/visual_script/visual_script_expression.cpp

@@ -377,13 +377,13 @@ Error VisualScriptExpression::_get_token(Token &r_token) {
 										r_token.type = TK_ERROR;
 										return ERR_PARSE_ERROR;
 									}
-									if (!((c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'))) {
+									if (!is_hex_digit(c)) {
 										_set_error("Malformed hex constant in string");
 										r_token.type = TK_ERROR;
 										return ERR_PARSE_ERROR;
 									}
 									char32_t v;
-									if (c >= '0' && c <= '9') {
+									if (is_digit(c)) {
 										v = c - '0';
 									} else if (c >= 'a' && c <= 'f') {
 										v = c - 'a';
@@ -457,7 +457,7 @@ Error VisualScriptExpression::_get_token(Token &r_token) {
 					break;
 				}
 
-				if (cchar >= '0' && cchar <= '9') {
+				if (is_digit(cchar)) {
 					//a number
 
 					String num;
@@ -476,7 +476,7 @@ Error VisualScriptExpression::_get_token(Token &r_token) {
 					while (true) {
 						switch (reading) {
 							case READING_INT: {
-								if (c >= '0' && c <= '9') {
+								if (is_digit(c)) {
 									//pass
 								} else if (c == '.') {
 									reading = READING_DEC;
@@ -489,7 +489,7 @@ Error VisualScriptExpression::_get_token(Token &r_token) {
 
 							} break;
 							case READING_DEC: {
-								if (c >= '0' && c <= '9') {
+								if (is_digit(c)) {
 								} else if (c == 'e') {
 									reading = READING_EXP;
 
@@ -499,7 +499,7 @@ Error VisualScriptExpression::_get_token(Token &r_token) {
 
 							} break;
 							case READING_EXP: {
-								if (c >= '0' && c <= '9') {
+								if (is_digit(c)) {
 									exp_beg = true;
 
 								} else if ((c == '-' || c == '+') && !exp_sign && !exp_beg) {
@@ -532,11 +532,11 @@ Error VisualScriptExpression::_get_token(Token &r_token) {
 					}
 					return OK;
 
-				} else if ((cchar >= 'A' && cchar <= 'Z') || (cchar >= 'a' && cchar <= 'z') || cchar == '_') {
+				} else if (is_ascii_char(cchar) || cchar == '_') {
 					String id;
 					bool first = true;
 
-					while ((cchar >= 'A' && cchar <= 'Z') || (cchar >= 'a' && cchar <= 'z') || cchar == '_' || (!first && cchar >= '0' && cchar <= '9')) {
+					while (is_ascii_char(cchar) || cchar == '_' || (!first && is_digit(cchar))) {
 						id += String::chr(cchar);
 						cchar = GET_CHAR();
 						first = false;

platform/android/export/export_plugin.cpp

@@ -416,10 +416,10 @@ String EditorExportPlatformAndroid::get_package_name(const String &p_package) co
 	bool first = true;
 	for (int i = 0; i < basename.length(); i++) {
 		char32_t c = basename[i];
-		if (c >= '0' && c <= '9' && first) {
+		if (is_digit(c) && first) {
 			continue;
 		}
-		if ((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9')) {
+		if (is_ascii_alphanumeric_char(c)) {
 			name += String::chr(c);
 			first = false;
 		}
@@ -462,19 +462,19 @@ bool EditorExportPlatformAndroid::is_package_name_valid(const String &p_package,
 			first = true;
 			continue;
 		}
-		if (!((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_')) {
+		if (!is_ascii_identifier_char(c)) {
 			if (r_error) {
 				*r_error = vformat(TTR("The character '%s' is not allowed in Android application package names."), String::chr(c));
 			}
 			return false;
 		}
-		if (first && (c >= '0' && c <= '9')) {
+		if (first && is_digit(c)) {
 			if (r_error) {
 				*r_error = TTR("A digit cannot be the first character in a package segment.");
 			}
 			return false;
 		}
-		if (first && c == '_') {
+		if (first && is_underscore(c)) {
 			if (r_error) {
 				*r_error = vformat(TTR("The character '%s' cannot be the first character in a package segment."), String::chr(c));
 			}

platform/iphone/export/export_plugin.h

@@ -130,7 +130,7 @@ class EditorExportPlatformIOS : public EditorExportPlatform {
 
 		for (int i = 0; i < pname.length(); i++) {
 			char32_t c = pname[i];
-			if (!((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '-' || c == '.')) {
+			if (!(is_ascii_alphanumeric_char(c) || c == '-' || c == '.')) {
 				if (r_error) {
 					*r_error = vformat(TTR("The character '%s' is not allowed in Identifier."), String::chr(c));
 				}

platform/linuxbsd/display_server_x11.cpp

@@ -2417,7 +2417,7 @@ Key DisplayServerX11::keyboard_get_keycode_from_physical(Key p_keycode) const {
 	Key keycode_no_mod = p_keycode & KeyModifierMask::CODE_MASK;
 	unsigned int xkeycode = KeyMappingX11::get_xlibcode(keycode_no_mod);
 	KeySym xkeysym = XkbKeycodeToKeysym(x11_display, xkeycode, 0, 0);
-	if (xkeysym >= 'a' && xkeysym <= 'z') {
+	if (is_ascii_lower_case(xkeysym)) {
 		xkeysym -= ('a' - 'A');
 	}
 

platform/osx/export/export_plugin.h

@@ -87,7 +87,7 @@ class EditorExportPlatformOSX : public EditorExportPlatform {
 
 		for (int i = 0; i < pname.length(); i++) {
 			char32_t c = pname[i];
-			if (!((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '-' || c == '.')) {
+			if (!(is_ascii_alphanumeric_char(c) || c == '-' || c == '.')) {
 				if (r_error) {
 					*r_error = vformat(TTR("The character '%s' is not allowed in Identifier."), String::chr(c));
 				}

scene/gui/code_edit.cpp

@@ -34,14 +34,6 @@
 #include "core/string/string_builder.h"
 #include "core/string/ustring.h"
 
-static bool _is_whitespace(char32_t c) {
-	return c == '\t' || c == ' ';
-}
-
-static bool _is_char(char32_t c) {
-	return !is_symbol(c);
-}
-
 void CodeEdit::_notification(int p_what) {
 	switch (p_what) {
 		case NOTIFICATION_THEME_CHANGED:
@@ -607,9 +599,9 @@ void CodeEdit::_handle_unicode_input_internal(const uint32_t p_unicode) {
 
 			int post_brace_pair = cc < get_line(cl).length() ? _get_auto_brace_pair_close_at_pos(cl, cc) : -1;
 
-			if (has_string_delimiter(chr) && cc > 0 && _is_char(get_line(cl)[cc - 1]) && post_brace_pair == -1) {
+			if (has_string_delimiter(chr) && cc > 0 && !is_symbol(get_line(cl)[cc - 1]) && post_brace_pair == -1) {
 				insert_text_at_caret(chr);
-			} else if (cc < get_line(cl).length() && _is_char(get_line(cl)[cc])) {
+			} else if (cc < get_line(cl).length() && !is_symbol(get_line(cl)[cc])) {
 				insert_text_at_caret(chr);
 			} else if (post_brace_pair != -1 && auto_brace_completion_pairs[post_brace_pair].close_key[0] == chr[0]) {
 				caret_move_offset = auto_brace_completion_pairs[post_brace_pair].close_key.length();
@@ -1001,7 +993,7 @@ void CodeEdit::_new_line(bool p_split_current_line, bool p_above) {
 			}
 
 			/* Make sure this is the last char, trailing whitespace or comments are okay. */
-			if (should_indent && (!_is_whitespace(c) && is_in_comment(cl, cc) == -1)) {
+			if (should_indent && (!is_whitespace(c) && is_in_comment(cl, cc) == -1)) {
 				should_indent = false;
 			}
 		}
@@ -1817,7 +1809,7 @@ void CodeEdit::request_code_completion(bool p_force) {
 	String line = get_line(get_caret_line());
 	int ofs = CLAMP(get_caret_column(), 0, line.length());
 
-	if (ofs > 0 && (is_in_string(get_caret_line(), ofs) != -1 || _is_char(line[ofs - 1]) || code_completion_prefixes.has(line[ofs - 1]))) {
+	if (ofs > 0 && (is_in_string(get_caret_line(), ofs) != -1 || !is_symbol(line[ofs - 1]) || code_completion_prefixes.has(line[ofs - 1]))) {
 		emit_signal(SNAME("code_completion_requested"));
 	} else if (ofs > 1 && line[ofs - 1] == ' ' && code_completion_prefixes.has(line[ofs - 2])) {
 		emit_signal(SNAME("code_completion_requested"));
@@ -1926,7 +1918,7 @@ void CodeEdit::confirm_code_completion(bool p_replace) {
 
 		if (merge_text) {
 			for (; caret_col < line.length(); caret_col++) {
-				if (!_is_char(line[caret_col])) {
+				if (is_symbol(line[caret_col])) {
 					break;
 				}
 			}
@@ -2562,7 +2554,7 @@ int CodeEdit::_is_in_delimiter(int p_line, int p_column, DelimiterType p_type) c
 			region = E->value();
 			in_region = true;
 			for (int i = E->key() - 2; i >= 0; i--) {
-				if (!_is_whitespace(line[i])) {
+				if (!is_whitespace(line[i])) {
 					return -1;
 				}
 			}
@@ -2581,7 +2573,7 @@ int CodeEdit::_is_in_delimiter(int p_line, int p_column, DelimiterType p_type) c
 		}
 
 		for (int i = end_col; i < line.length(); i++) {
-			if (!_is_whitespace(line[i])) {
+			if (!is_whitespace(line[i])) {
 				return -1;
 			}
 		}
@@ -2797,11 +2789,11 @@ void CodeEdit::_filter_code_completion_candidates_impl() {
 		while (ofs > 0 && line[ofs] == ' ') {
 			ofs--;
 		}
-		prev_is_word = _is_char(line[ofs]);
+		prev_is_word = !is_symbol(line[ofs]);
 		/* Otherwise get current word and set cofs to the start. */
 	} else {
 		int start_cofs = cofs;
-		while (cofs > 0 && line[cofs - 1] > 32 && (line[cofs - 1] == '/' || _is_char(line[cofs - 1]))) {
+		while (cofs > 0 && line[cofs - 1] > 32 && (line[cofs - 1] == '/' || !is_symbol(line[cofs - 1]))) {
 			cofs--;
 		}
 		string_to_complete = line.substr(cofs, start_cofs - cofs);

scene/gui/text_edit.cpp

@@ -43,18 +43,6 @@
 
 #include "scene/main/window.h"
 
-static bool _is_text_char(char32_t c) {
-	return !is_symbol(c);
-}
-
-static bool _is_whitespace(char32_t c) {
-	return c == '\t' || c == ' ';
-}
-
-static bool _is_char(char32_t c) {
-	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || c == '_';
-}
-
 ///////////////////////////////////////////////////////////////////////////////
 ///                            TEXT                                         ///
 ///////////////////////////////////////////////////////////////////////////////
@@ -820,8 +808,8 @@ void TextEdit::_notification(int p_what) {
 							int xpos = indent_px + ((xmargin_end + minimap_char_size.x) + (minimap_char_size.x * j)) + tabs;
 							bool out_of_bounds = (xpos >= xmargin_end + minimap_width);
 
-							bool is_whitespace = _is_whitespace(str[j]);
-							if (!is_whitespace) {
+							bool whitespace = is_whitespace(str[j]);
+							if (!whitespace) {
 								characters++;
 
 								if (j < str.length() - 1 && color == previous_color && !out_of_bounds) {
@@ -843,7 +831,7 @@ void TextEdit::_notification(int p_what) {
 							if (characters > 0) {
 								previous_color.a *= 0.6;
 								// take one for zero indexing, and if we hit whitespace / the end of a word.
-								int chars = MAX(0, (j - (characters - 1)) - (is_whitespace ? 1 : 0)) + 1;
+								int chars = MAX(0, (j - (characters - 1)) - (whitespace ? 1 : 0)) + 1;
 								int char_x_ofs = indent_px + ((xmargin_end + minimap_char_size.x) + (minimap_char_size.x * chars)) + tabs;
 								if (rtl) {
 									RenderingServer::get_singleton()->canvas_item_add_rect(ci, Rect2(Point2(size.width - char_x_ofs - minimap_char_size.x * characters, minimap_line_height * i), Point2(minimap_char_size.x * characters, minimap_char_size.y)), previous_color);
@@ -1144,7 +1132,7 @@ void TextEdit::_notification(int p_what) {
 					}
 
 					if (!clipped && lookup_symbol_word.length() != 0) { // Highlight word
-						if (_is_char(lookup_symbol_word[0]) || lookup_symbol_word[0] == '.') {
+						if (is_ascii_char(lookup_symbol_word[0]) || lookup_symbol_word[0] == '_' || lookup_symbol_word[0] == '.') {
 							int highlighted_word_col = _get_column_pos_of_word(lookup_symbol_word, str, SEARCH_MATCH_CASE | SEARCH_WHOLE_WORDS, 0);
 							while (highlighted_word_col != -1) {
 								Vector<Vector2> sel = TS->shaped_text_get_selection(rid, highlighted_word_col + start, highlighted_word_col + lookup_symbol_word.length() + start);
@@ -3037,7 +3025,7 @@ int TextEdit::get_first_non_whitespace_column(int p_line) const {
 	ERR_FAIL_INDEX_V(p_line, text.size(), 0);
 
 	int col = 0;
-	while (col < text[p_line].length() && _is_whitespace(text[p_line][col])) {
+	while (col < text[p_line].length() && is_whitespace(text[p_line][col])) {
 		col++;
 	}
 	return col;
@@ -3622,9 +3610,9 @@ Point2i TextEdit::search(const String &p_key, uint32_t p_search_flags, int p_fro
 
 			if (pos != -1 && (p_search_flags & SEARCH_WHOLE_WORDS)) {
 				// Validate for whole words.
-				if (pos > 0 && _is_text_char(text_line[pos - 1])) {
+				if (pos > 0 && !is_symbol(text_line[pos - 1])) {
 					is_match = false;
-				} else if (pos + p_key.length() < text_line.length() && _is_text_char(text_line[pos + p_key.length()])) {
+				} else if (pos + p_key.length() < text_line.length() && !is_symbol(text_line[pos + p_key.length()])) {
 					is_match = false;
 				}
 			}
@@ -5779,9 +5767,9 @@ int TextEdit::_get_column_pos_of_word(const String &p_key, const String &p_searc
 			if (col != -1 && p_search_flags & SEARCH_WHOLE_WORDS) {
 				p_from_column = col;
 
-				if (col > 0 && _is_text_char(p_search[col - 1])) {
+				if (col > 0 && !is_symbol(p_search[col - 1])) {
 					col = -1;
-				} else if ((col + p_key.length()) < p_search.length() && _is_text_char(p_search[col + p_key.length()])) {
+				} else if ((col + p_key.length()) < p_search.length() && !is_symbol(p_search[col + p_key.length()])) {
 					col = -1;
 				}
 			}

scene/main/node.cpp

@@ -1061,7 +1061,7 @@ void Node::_generate_serial_child_name(const Node *p_child, StringName &name) co
 	String nums;
 	for (int i = name_string.length() - 1; i >= 0; i--) {
 		char32_t n = name_string[i];
-		if (n >= '0' && n <= '9') {
+		if (is_digit(n)) {
 			nums = String::chr(name_string[i]) + nums;
 		} else {
 			break;

scene/property_utils.cpp

@@ -130,7 +130,7 @@ Variant PropertyUtils::get_property_default_value(const Object *p_object, const
 			if (p != -1 && p < prop_str.length() - 1) {
 				bool all_digits = true;
 				for (int i = p + 1; i < prop_str.length(); i++) {
-					if (prop_str[i] < '0' || prop_str[i] > '9') {
+					if (!is_digit(prop_str[i])) {
 						all_digits = false;
 						break;
 					}

scene/resources/syntax_highlighter.cpp

@@ -116,14 +116,6 @@ void SyntaxHighlighter::_bind_methods() {
 
 ////////////////////////////////////////////////////////////////////////////////
 
-static bool _is_char(char32_t c) {
-	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || c == '_';
-}
-
-static bool _is_hex_symbol(char32_t c) {
-	return ((c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'));
-}
-
 Dictionary CodeHighlighter::_get_line_syntax_highlighting_impl(int p_line) {
 	Dictionary color_map;
 
@@ -166,7 +158,7 @@ Dictionary CodeHighlighter::_get_line_syntax_highlighting_impl(int p_line) {
 		color = font_color;
 		bool is_char = !is_symbol(str[j]);
 		bool is_a_symbol = is_symbol(str[j]);
-		bool is_number = (str[j] >= '0' && str[j] <= '9');
+		bool is_number = is_digit(str[j]);
 
 		/* color regions */
 		if (is_a_symbol || in_region != -1) {
@@ -304,7 +296,7 @@ Dictionary CodeHighlighter::_get_line_syntax_highlighting_impl(int p_line) {
 		}
 
 		// Allow ABCDEF in hex notation.
-		if (is_hex_notation && (_is_hex_symbol(str[j]) || is_number)) {
+		if (is_hex_notation && (is_hex_digit(str[j]) || is_number)) {
 			is_number = true;
 		} else {
 			is_hex_notation = false;
@@ -321,7 +313,7 @@ Dictionary CodeHighlighter::_get_line_syntax_highlighting_impl(int p_line) {
 			}
 		}
 
-		if (!in_word && _is_char(str[j]) && !is_number) {
+		if (!in_word && (is_ascii_char(str[j]) || is_underscore(str[j])) && !is_number) {
 			in_word = true;
 		}
 

scene/resources/visual_shader.cpp

@@ -1106,10 +1106,6 @@ String VisualShader::generate_preview_shader(Type p_type, int p_node, int p_port
 	return final_code;
 }
 
-#define IS_INITIAL_CHAR(m_d) (((m_d) >= 'a' && (m_d) <= 'z') || ((m_d) >= 'A' && (m_d) <= 'Z'))
-
-#define IS_SYMBOL_CHAR(m_d) (((m_d) >= 'a' && (m_d) <= 'z') || ((m_d) >= 'A' && (m_d) <= 'Z') || ((m_d) >= '0' && (m_d) <= '9') || (m_d) == '_')
-
 String VisualShader::validate_port_name(const String &p_port_name, VisualShaderNode *p_node, int p_port_id, bool p_output) const {
 	String name = p_port_name;
 
@@ -1117,7 +1113,7 @@ String VisualShader::validate_port_name(const String &p_port_name, VisualShaderN
 		return String();
 	}
 
-	while (name.length() && !IS_INITIAL_CHAR(name[0])) {
+	while (name.length() && !is_ascii_char(name[0])) {
 		name = name.substr(1, name.length() - 1);
 	}
 
@@ -1125,7 +1121,7 @@ String VisualShader::validate_port_name(const String &p_port_name, VisualShaderN
 		String valid_name;
 
 		for (int i = 0; i < name.length(); i++) {
-			if (IS_SYMBOL_CHAR(name[i])) {
+			if (is_ascii_identifier_char(name[i])) {
 				valid_name += String::chr(name[i]);
 			} else if (name[i] == ' ') {
 				valid_name += "_";
@@ -1162,14 +1158,14 @@ String VisualShader::validate_port_name(const String &p_port_name, VisualShaderN
 
 String VisualShader::validate_uniform_name(const String &p_name, const Ref<VisualShaderNodeUniform> &p_uniform) const {
 	String name = p_name; //validate name first
-	while (name.length() && !IS_INITIAL_CHAR(name[0])) {
+	while (name.length() && !is_ascii_char(name[0])) {
 		name = name.substr(1, name.length() - 1);
 	}
 	if (!name.is_empty()) {
 		String valid_name;
 
 		for (int i = 0; i < name.length(); i++) {
-			if (IS_SYMBOL_CHAR(name[i])) {
+			if (is_ascii_identifier_char(name[i])) {
 				valid_name += String::chr(name[i]);
 			} else if (name[i] == ' ') {
 				valid_name += "_";
@@ -1206,7 +1202,7 @@ String VisualShader::validate_uniform_name(const String &p_name, const Ref<Visua
 		if (exists) {
 			//remove numbers, put new and try again
 			attempt++;
-			while (name.length() && name[name.length() - 1] >= '0' && name[name.length() - 1] <= '9') {
+			while (name.length() && is_digit(name[name.length() - 1])) {
 				name = name.substr(0, name.length() - 1);
 			}
 			ERR_FAIL_COND_V(name.is_empty(), String());

servers/rendering/shader_language.cpp

@@ -35,18 +35,6 @@
 
 #define HAS_WARNING(flag) (warning_flags & flag)
 
-static bool _is_text_char(char32_t c) {
-	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_';
-}
-
-static bool _is_number(char32_t c) {
-	return (c >= '0' && c <= '9');
-}
-
-static bool _is_hex(char32_t c) {
-	return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F');
-}
-
 String ShaderLanguage::get_operator_text(Operator p_op) {
 	static const char *op_names[OP_MAX] = { "==",
 		"!=",
@@ -543,7 +531,7 @@ ShaderLanguage::Token ShaderLanguage::_get_token() {
 			default: {
 				char_idx--; //go back one, since we have no idea what this is
 
-				if (_is_number(GETCHAR(0)) || (GETCHAR(0) == '.' && _is_number(GETCHAR(1)))) {
+				if (is_digit(GETCHAR(0)) || (GETCHAR(0) == '.' && is_digit(GETCHAR(1)))) {
 					// parse number
 					bool hexa_found = false;
 					bool period_found = false;
@@ -584,7 +572,7 @@ ShaderLanguage::Token ShaderLanguage::_get_token() {
 						const char32_t symbol = String::char_lowercase(GETCHAR(i));
 						bool error = false;
 
-						if (_is_number(symbol)) {
+						if (is_digit(symbol)) {
 							if (end_suffix_found) {
 								error = true;
 							}
@@ -617,8 +605,8 @@ ShaderLanguage::Token ShaderLanguage::_get_token() {
 										break;
 									}
 								}
-							} else if (!hexa_found || !_is_hex(symbol)) {
-								if (_is_text_char(symbol)) {
+							} else if (!hexa_found || !is_hex_digit(symbol)) {
+								if (is_ascii_identifier_char(symbol)) {
 									error = true;
 								} else {
 									break;
@@ -649,7 +637,7 @@ ShaderLanguage::Token ShaderLanguage::_get_token() {
 							return _make_token(TK_ERROR, "Invalid (hexadecimal) numeric constant");
 						}
 					} else if (period_found || exponent_found || float_suffix_found) { // Float
-						if (exponent_found && (!_is_number(last_char) && last_char != 'f')) { // checks for eg: "2E", "2E-", "2E+"
+						if (exponent_found && (!is_digit(last_char) && last_char != 'f')) { // checks for eg: "2E", "2E-", "2E+"
 							return _make_token(TK_ERROR, "Invalid (float) numeric constant");
 						}
 						if (period_found) {
@@ -660,7 +648,7 @@ ShaderLanguage::Token ShaderLanguage::_get_token() {
 								}
 							} else {
 								//checks for eg. "1." or "1.99" notations
-								if (last_char != '.' && !_is_number(last_char)) {
+								if (last_char != '.' && !is_digit(last_char)) {
 									return _make_token(TK_ERROR, "Invalid (float) numeric constant");
 								}
 							}
@@ -723,11 +711,11 @@ ShaderLanguage::Token ShaderLanguage::_get_token() {
 					return _make_token(TK_PERIOD);
 				}
 
-				if (_is_text_char(GETCHAR(0))) {
+				if (is_ascii_identifier_char(GETCHAR(0))) {
 					// parse identifier
 					String str;
 
-					while (_is_text_char(GETCHAR(0))) {
+					while (is_ascii_identifier_char(GETCHAR(0))) {
 						str += char32_t(GETCHAR(0));
 						char_idx++;
 					}

tests/core/math/test_math.cpp

@@ -227,7 +227,7 @@ class GetClassAndNamespace {
 						return TK_SYMBOL;
 					}
 
-					if (code[idx] == '-' || (code[idx] >= '0' && code[idx] <= '9')) {
+					if (code[idx] == '-' || is_digit(code[idx])) {
 						//a number
 						const char32_t *rptr;
 						double number = String::to_float(&code[idx], &rptr);
@@ -235,10 +235,10 @@ class GetClassAndNamespace {
 						value = number;
 						return TK_NUMBER;
 
-					} else if ((code[idx] >= 'A' && code[idx] <= 'Z') || (code[idx] >= 'a' && code[idx] <= 'z') || code[idx] > 127) {
+					} else if (is_ascii_char(code[idx]) || code[idx] > 127) {
 						String id;
 
-						while ((code[idx] >= 'A' && code[idx] <= 'Z') || (code[idx] >= 'a' && code[idx] <= 'z') || code[idx] > 127) {
+						while (is_ascii_char(code[idx]) || code[idx] > 127) {
 							id += code[idx];
 							idx++;
 						}