summaryrefslogtreecommitdiff
path: root/core/string/ustring.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'core/string/ustring.cpp')
-rw-r--r--core/string/ustring.cpp345
1 files changed, 135 insertions, 210 deletions
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;
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-14 18:18:56 +0000