mirror of
https://github.com/ArthurSonzogni/FTXUI.git
synced 2025-09-19 18:18:09 +08:00
Prefer std::string over std::wstring. (#179)
In the past, FTXUI switched from std::string to std::wstring to support fullwidth characters. The reasons was that fullwidth characters can be stored inside a single wchar_t. Then FTXUI added support for combining characters. A single glygh doesn't even fit a wchar_t. Instead, a glyph can be arbitrary large. The usage of wstring doesn't really fit the new model and have several drawbacks: 1. It doesn't simplify the implementation of FTXUI, because of combining characters. 2. It reduces drawing performance by 2x. 3. It increase Screen's memory allocation by 2x. This patch converts FTXUI to use std::string internally. It now exposes std::string based API. The std::wstring API remains, but is now deprecated. Tests and examples haven't been update to show the breakage is limited. They will be updated in a second set of patches. Bug: https://github.com/ArthurSonzogni/FTXUI/issues/153 Co-authored-by: Tushar Maheshwari <tushar27192@gmail.com>
This commit is contained in:
Arthur Sonzogni
@@ -1,19 +1,16 @@
|
||||
#include "ftxui/screen/color.hpp"
|
||||
#include "ftxui/screen/color_info.hpp"
|
||||
#include "ftxui/screen/string.hpp"
|
||||
#include "ftxui/screen/terminal.hpp"
|
||||
|
||||
#include "ftxui/screen/color_info.hpp" // for GetColorInfo, ColorInfo
|
||||
#include "ftxui/screen/terminal.hpp" // for Terminal, Terminal::Color, Terminal::Palette256, Terminal::TrueColor
|
||||
|
||||
namespace ftxui {
|
||||
|
||||
namespace {
|
||||
const wchar_t* palette16code[16][2] = {
|
||||
{L"30", L"40"}, {L"31", L"41"}, {L"32", L"42"}, {L"33", L"43"},
|
||||
{L"34", L"44"},
|
||||
|
||||
{L"35", L"45"}, {L"36", L"46"}, {L"37", L"47"},
|
||||
|
||||
{L"90", L"100"}, {L"91", L"101"}, {L"92", L"102"}, {L"93", L"103"},
|
||||
{L"94", L"104"}, {L"95", L"105"}, {L"96", L"106"}, {L"97", L"107"},
|
||||
const char* palette16code[16][2] = {
|
||||
{"30", "40"}, {"31", "41"}, {"32", "42"}, {"33", "43"},
|
||||
{"34", "44"}, {"35", "45"}, {"36", "46"}, {"37", "47"},
|
||||
{"90", "100"}, {"91", "101"}, {"92", "102"}, {"93", "103"},
|
||||
{"94", "104"}, {"95", "105"}, {"96", "106"}, {"97", "107"},
|
||||
};
|
||||
}
|
||||
|
||||
@@ -26,24 +23,24 @@ bool Color::operator!=(const Color& rhs) const {
|
||||
return !operator==(rhs);
|
||||
}
|
||||
|
||||
std::wstring Color::Print(bool is_background_color) const {
|
||||
std::string Color::Print(bool is_background_color) const {
|
||||
switch (type_) {
|
||||
case ColorType::Palette1:
|
||||
return is_background_color ? L"49" : L"39";
|
||||
return is_background_color ? "49" : "39";
|
||||
|
||||
case ColorType::Palette16:
|
||||
return palette16code[index_][is_background_color];
|
||||
|
||||
case ColorType::Palette256:
|
||||
return (is_background_color ? L"48;5;" : L"38;5;") + to_wstring(index_);
|
||||
return (is_background_color ? "48;5;" : "38;5;") + std::to_string(index_);
|
||||
|
||||
case ColorType::TrueColor:
|
||||
return (is_background_color ? L"48;2;" : L"38;2;") //
|
||||
+ to_wstring(red_) + L";" //
|
||||
+ to_wstring(green_) + L";" //
|
||||
+ to_wstring(blue_); //
|
||||
return (is_background_color ? "48;2;" : "38;2;") //
|
||||
+ std::to_string(red_) + ";" //
|
||||
+ std::to_string(green_) + ";" //
|
||||
+ std::to_string(blue_); //
|
||||
}
|
||||
return L"";
|
||||
return "";
|
||||
}
|
||||
|
||||
/// @brief Build a transparent color.
|
||||
|
||||
@@ -1,10 +1,9 @@
|
||||
#include <algorithm> // for max
|
||||
#include <iostream> // for operator<<, basic_ostream, wstringstream, stringstream, flush, cout, ostream
|
||||
#include <memory> // for allocator
|
||||
#include <sstream> // IWYU pragma: keep
|
||||
#include <iostream> // for operator<<, stringstream, basic_ostream, flush, cout, ostream
|
||||
#include <memory> // for allocator
|
||||
#include <sstream> // IWYU pragma: keep
|
||||
|
||||
#include "ftxui/screen/screen.hpp"
|
||||
#include "ftxui/screen/string.hpp" // for to_string, wchar_width
|
||||
#include "ftxui/screen/string.hpp" // for string_width
|
||||
#include "ftxui/screen/terminal.hpp" // for Dimensions, Size
|
||||
|
||||
#if defined(_WIN32)
|
||||
@@ -18,24 +17,24 @@
|
||||
namespace ftxui {
|
||||
|
||||
namespace {
|
||||
static const wchar_t* BOLD_SET = L"\x1B[1m";
|
||||
static const wchar_t* BOLD_RESET = L"\x1B[22m"; // Can't use 21 here.
|
||||
static const char BOLD_SET[] = "\x1B[1m";
|
||||
static const char BOLD_RESET[] = "\x1B[22m"; // Can't use 21 here.
|
||||
|
||||
static const wchar_t* DIM_SET = L"\x1B[2m";
|
||||
static const wchar_t* DIM_RESET = L"\x1B[22m";
|
||||
static const char DIM_SET[] = "\x1B[2m";
|
||||
static const char DIM_RESET[] = "\x1B[22m";
|
||||
|
||||
static const wchar_t* UNDERLINED_SET = L"\x1B[4m";
|
||||
static const wchar_t* UNDERLINED_RESET = L"\x1B[24m";
|
||||
static const char UNDERLINED_SET[] = "\x1B[4m";
|
||||
static const char UNDERLINED_RESET[] = "\x1B[24m";
|
||||
|
||||
static const wchar_t* BLINK_SET = L"\x1B[5m";
|
||||
static const wchar_t* BLINK_RESET = L"\x1B[25m";
|
||||
static const char BLINK_SET[] = "\x1B[5m";
|
||||
static const char BLINK_RESET[] = "\x1B[25m";
|
||||
|
||||
static const wchar_t* INVERTED_SET = L"\x1B[7m";
|
||||
static const wchar_t* INVERTED_RESET = L"\x1B[27m";
|
||||
static const char INVERTED_SET[] = "\x1B[7m";
|
||||
static const char INVERTED_RESET[] = "\x1B[27m";
|
||||
|
||||
static const char* MOVE_LEFT = "\r";
|
||||
static const char* MOVE_UP = "\x1B[1A";
|
||||
static const char* CLEAR_LINE = "\x1B[2K";
|
||||
static const char MOVE_LEFT[] = "\r";
|
||||
static const char MOVE_UP[] = "\x1B[1A";
|
||||
static const char CLEAR_LINE[] = "\x1B[2K";
|
||||
|
||||
Pixel dev_null_pixel;
|
||||
|
||||
@@ -62,7 +61,9 @@ void WindowsEmulateVT100Terminal() {
|
||||
}
|
||||
#endif
|
||||
|
||||
void UpdatePixelStyle(std::wstringstream& ss, Pixel& previous, Pixel& next) {
|
||||
void UpdatePixelStyle(std::stringstream& ss,
|
||||
Pixel& previous,
|
||||
const Pixel& next) {
|
||||
if (next.bold != previous.bold)
|
||||
ss << (next.bold ? BOLD_SET : BOLD_RESET);
|
||||
|
||||
@@ -80,8 +81,8 @@ void UpdatePixelStyle(std::wstringstream& ss, Pixel& previous, Pixel& next) {
|
||||
|
||||
if (next.foreground_color != previous.foreground_color ||
|
||||
next.background_color != previous.background_color) {
|
||||
ss << L"\x1B[" + next.foreground_color.Print(false) + L"m";
|
||||
ss << L"\x1B[" + next.background_color.Print(true) + L"m";
|
||||
ss << "\x1B[" + next.foreground_color.Print(false) + "m";
|
||||
ss << "\x1B[" + next.background_color.Print(true) + "m";
|
||||
}
|
||||
|
||||
previous = next;
|
||||
@@ -135,7 +136,7 @@ Screen::Screen(int dimx, int dimy)
|
||||
/// Produce a std::string that can be used to print the Screen on the terminal.
|
||||
/// Don't forget to flush stdout. Alternatively, you can use Screen::Print();
|
||||
std::string Screen::ToString() {
|
||||
std::wstringstream ss;
|
||||
std::stringstream ss;
|
||||
|
||||
Pixel previous_pixel;
|
||||
Pixel final_pixel;
|
||||
@@ -143,24 +144,21 @@ std::string Screen::ToString() {
|
||||
for (int y = 0; y < dimy_; ++y) {
|
||||
if (y != 0) {
|
||||
UpdatePixelStyle(ss, previous_pixel, final_pixel);
|
||||
ss << L"\r\n";
|
||||
ss << "\r\n";
|
||||
}
|
||||
for (int x = 0; x < dimx_;) {
|
||||
auto& pixel = pixels_[y][x];
|
||||
UpdatePixelStyle(ss, previous_pixel, pixel);
|
||||
|
||||
int x_inc = 0;
|
||||
for (auto& c : pixel.character) {
|
||||
ss << c;
|
||||
x_inc += wchar_width(c);
|
||||
bool previous_fullwidth = false;
|
||||
for (const auto& pixel : pixels_[y]) {
|
||||
if (!previous_fullwidth) {
|
||||
UpdatePixelStyle(ss, previous_pixel, pixel);
|
||||
ss << pixel.character;
|
||||
}
|
||||
x += std::max(x_inc, 1);
|
||||
previous_fullwidth = (string_width(pixel.character) == 2);
|
||||
}
|
||||
}
|
||||
|
||||
UpdatePixelStyle(ss, previous_pixel, final_pixel);
|
||||
|
||||
return to_string(ss.str());
|
||||
return ss.str();
|
||||
}
|
||||
|
||||
void Screen::Print() {
|
||||
@@ -170,8 +168,8 @@ void Screen::Print() {
|
||||
/// @brief Access a character a given position.
|
||||
/// @param x The character position along the x-axis.
|
||||
/// @param y The character position along the y-axis.
|
||||
wchar_t& Screen::at(int x, int y) {
|
||||
return PixelAt(x, y).character[0];
|
||||
std::string& Screen::at(int x, int y) {
|
||||
return PixelAt(x, y).character;
|
||||
}
|
||||
|
||||
/// @brief Access a Pixel at a given position.
|
||||
@@ -229,21 +227,21 @@ void Screen::ApplyShader() {
|
||||
// Merge box characters togethers.
|
||||
for (int y = 1; y < dimy_; ++y) {
|
||||
for (int x = 1; x < dimx_; ++x) {
|
||||
wchar_t& left = at(x - 1, y);
|
||||
wchar_t& top = at(x, y - 1);
|
||||
wchar_t& cur = at(x, y);
|
||||
std::string& left = at(x - 1, y);
|
||||
std::string& top = at(x, y - 1);
|
||||
std::string& cur = at(x, y);
|
||||
|
||||
// Left vs current
|
||||
if (cur == U'│' && left == U'─') cur = U'┤';
|
||||
if (cur == U'─' && left == U'│') left = U'├';
|
||||
if (cur == U'├' && left == U'─') cur = U'┼';
|
||||
if (cur == U'─' && left == U'┤') left = U'┼';
|
||||
if (cur == "│" && left == "─") cur = "┤";
|
||||
if (cur == "─" && left == "│") left = "├";
|
||||
if (cur == "├" && left == "─") cur = "┼";
|
||||
if (cur == "─" && left == "┤") left = "┼";
|
||||
|
||||
// Top vs current
|
||||
if (cur == U'─' && top == U'│') cur = U'┴';
|
||||
if (cur == U'│' && top == U'─') top = U'┬';
|
||||
if (cur == U'┬' && top == U'│') cur = U'┼';
|
||||
if (cur == U'│' && top == U'┴') top = U'┼';
|
||||
if (cur == "─" && top == "│") cur = "┴";
|
||||
if (cur == "│" && top == "─") top = "┬";
|
||||
if (cur == "┬" && top == "│") cur = "┼";
|
||||
if (cur == "│" && top == "┴") top = "┼";
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,9 +1,291 @@
|
||||
// Most of this code is borrowed from:
|
||||
// Markus Kuhn -- 2007-05-26 (Unicode 5.0)
|
||||
// Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
|
||||
// Thanks you!
|
||||
//
|
||||
// Modified by Arthur Sonzogni for FTXUI.
|
||||
|
||||
#include "ftxui/screen/string.hpp"
|
||||
|
||||
#include <codecvt> // for codecvt_utf8_utf16
|
||||
#include <locale> // for wstring_convert
|
||||
#include <stddef.h> // for size_t
|
||||
#include <stdint.h> // for uint32_t, uint8_t
|
||||
#include <codecvt> // for codecvt_utf8_utf16
|
||||
#include <locale> // for wstring_convert
|
||||
#include <string> // for string, basic_string, wstring, allocator
|
||||
|
||||
namespace {
|
||||
|
||||
struct Interval {
|
||||
uint32_t first;
|
||||
uint32_t last;
|
||||
};
|
||||
|
||||
// Sorted list of non-overlapping intervals of non-spacing characters
|
||||
// generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c"
|
||||
static const Interval g_combining_characters[] = {
|
||||
{0x0300, 0x036F}, {0x0483, 0x0486}, {0x0488, 0x0489},
|
||||
{0x0591, 0x05BD}, {0x05BF, 0x05BF}, {0x05C1, 0x05C2},
|
||||
{0x05C4, 0x05C5}, {0x05C7, 0x05C7}, {0x0600, 0x0603},
|
||||
{0x0610, 0x0615}, {0x064B, 0x065E}, {0x0670, 0x0670},
|
||||
{0x06D6, 0x06E4}, {0x06E7, 0x06E8}, {0x06EA, 0x06ED},
|
||||
{0x070F, 0x070F}, {0x0711, 0x0711}, {0x0730, 0x074A},
|
||||
{0x07A6, 0x07B0}, {0x07EB, 0x07F3}, {0x0901, 0x0902},
|
||||
{0x093C, 0x093C}, {0x0941, 0x0948}, {0x094D, 0x094D},
|
||||
{0x0951, 0x0954}, {0x0962, 0x0963}, {0x0981, 0x0981},
|
||||
{0x09BC, 0x09BC}, {0x09C1, 0x09C4}, {0x09CD, 0x09CD},
|
||||
{0x09E2, 0x09E3}, {0x0A01, 0x0A02}, {0x0A3C, 0x0A3C},
|
||||
{0x0A41, 0x0A42}, {0x0A47, 0x0A48}, {0x0A4B, 0x0A4D},
|
||||
{0x0A70, 0x0A71}, {0x0A81, 0x0A82}, {0x0ABC, 0x0ABC},
|
||||
{0x0AC1, 0x0AC5}, {0x0AC7, 0x0AC8}, {0x0ACD, 0x0ACD},
|
||||
{0x0AE2, 0x0AE3}, {0x0B01, 0x0B01}, {0x0B3C, 0x0B3C},
|
||||
{0x0B3F, 0x0B3F}, {0x0B41, 0x0B43}, {0x0B4D, 0x0B4D},
|
||||
{0x0B56, 0x0B56}, {0x0B82, 0x0B82}, {0x0BC0, 0x0BC0},
|
||||
{0x0BCD, 0x0BCD}, {0x0C3E, 0x0C40}, {0x0C46, 0x0C48},
|
||||
{0x0C4A, 0x0C4D}, {0x0C55, 0x0C56}, {0x0CBC, 0x0CBC},
|
||||
{0x0CBF, 0x0CBF}, {0x0CC6, 0x0CC6}, {0x0CCC, 0x0CCD},
|
||||
{0x0CE2, 0x0CE3}, {0x0D41, 0x0D43}, {0x0D4D, 0x0D4D},
|
||||
{0x0DCA, 0x0DCA}, {0x0DD2, 0x0DD4}, {0x0DD6, 0x0DD6},
|
||||
{0x0E31, 0x0E31}, {0x0E34, 0x0E3A}, {0x0E47, 0x0E4E},
|
||||
{0x0EB1, 0x0EB1}, {0x0EB4, 0x0EB9}, {0x0EBB, 0x0EBC},
|
||||
{0x0EC8, 0x0ECD}, {0x0F18, 0x0F19}, {0x0F35, 0x0F35},
|
||||
{0x0F37, 0x0F37}, {0x0F39, 0x0F39}, {0x0F71, 0x0F7E},
|
||||
{0x0F80, 0x0F84}, {0x0F86, 0x0F87}, {0x0F90, 0x0F97},
|
||||
{0x0F99, 0x0FBC}, {0x0FC6, 0x0FC6}, {0x102D, 0x1030},
|
||||
{0x1032, 0x1032}, {0x1036, 0x1037}, {0x1039, 0x1039},
|
||||
{0x1058, 0x1059}, {0x1160, 0x11FF}, {0x135F, 0x135F},
|
||||
{0x1712, 0x1714}, {0x1732, 0x1734}, {0x1752, 0x1753},
|
||||
{0x1772, 0x1773}, {0x17B4, 0x17B5}, {0x17B7, 0x17BD},
|
||||
{0x17C6, 0x17C6}, {0x17C9, 0x17D3}, {0x17DD, 0x17DD},
|
||||
{0x180B, 0x180D}, {0x18A9, 0x18A9}, {0x1920, 0x1922},
|
||||
{0x1927, 0x1928}, {0x1932, 0x1932}, {0x1939, 0x193B},
|
||||
{0x1A17, 0x1A18}, {0x1B00, 0x1B03}, {0x1B34, 0x1B34},
|
||||
{0x1B36, 0x1B3A}, {0x1B3C, 0x1B3C}, {0x1B42, 0x1B42},
|
||||
{0x1B6B, 0x1B73}, {0x1DC0, 0x1DCA}, {0x1DFE, 0x1DFF},
|
||||
{0x200B, 0x200F}, {0x202A, 0x202E}, {0x2060, 0x2063},
|
||||
{0x206A, 0x206F}, {0x20D0, 0x20EF}, {0x302A, 0x302F},
|
||||
{0x3099, 0x309A}, {0xA806, 0xA806}, {0xA80B, 0xA80B},
|
||||
{0xA825, 0xA826}, {0xFB1E, 0xFB1E}, {0xFE00, 0xFE0F},
|
||||
{0xFE20, 0xFE23}, {0xFEFF, 0xFEFF}, {0xFFF9, 0xFFFB},
|
||||
{0x10A01, 0x10A03}, {0x10A05, 0x10A06}, {0x10A0C, 0x10A0F},
|
||||
{0x10A38, 0x10A3A}, {0x10A3F, 0x10A3F}, {0x1D167, 0x1D169},
|
||||
{0x1D173, 0x1D182}, {0x1D185, 0x1D18B}, {0x1D1AA, 0x1D1AD},
|
||||
{0x1D242, 0x1D244}, {0xE0001, 0xE0001}, {0xE0020, 0xE007F},
|
||||
{0xE0100, 0xE01EF},
|
||||
};
|
||||
|
||||
static const Interval g_full_width_characters[] = {
|
||||
{0x1100, 0x115f}, {0x2329, 0x2329}, {0x232a, 0x232a}, {0x2e80, 0x303e},
|
||||
{0x3040, 0xa4cf}, {0xac00, 0xd7a3}, {0xf900, 0xfaff}, {0xfe10, 0xfe19},
|
||||
{0xfe30, 0xfe6f}, {0xff00, 0xff60}, {0xffe0, 0xffe6}, {0x20000, 0x2fffd},
|
||||
{0x30000, 0x3fffd},
|
||||
};
|
||||
|
||||
// Find a codepoint inside a sorted list of Interval.
|
||||
int Bisearch(uint32_t ucs, const Interval* table, int max) {
|
||||
if (ucs < table[0].first || ucs > table[max].last)
|
||||
return 0;
|
||||
|
||||
int min = 0;
|
||||
while (max >= min) {
|
||||
int mid = (min + max) / 2;
|
||||
if (ucs > table[mid].last)
|
||||
min = mid + 1;
|
||||
else if (ucs < table[mid].first)
|
||||
max = mid - 1;
|
||||
else
|
||||
return 1;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
bool IsCombining(uint32_t ucs) {
|
||||
return Bisearch(ucs, g_combining_characters,
|
||||
sizeof(g_combining_characters) / sizeof(Interval) - 1);
|
||||
}
|
||||
|
||||
bool IsFullWidth(uint32_t ucs) {
|
||||
if (ucs < 0x0300) // Quick path:
|
||||
return false;
|
||||
|
||||
return Bisearch(ucs, g_full_width_characters,
|
||||
sizeof(g_full_width_characters) / sizeof(Interval) - 1);
|
||||
}
|
||||
|
||||
bool IsControl(uint32_t ucs) {
|
||||
if (ucs == 0)
|
||||
return true;
|
||||
if (ucs < 32)
|
||||
return true;
|
||||
if (ucs >= 0x7f && ucs < 0xa0)
|
||||
return true;
|
||||
return false;
|
||||
}
|
||||
|
||||
int codepoint_width(uint32_t ucs) {
|
||||
if (IsControl(ucs))
|
||||
return -1;
|
||||
|
||||
if (IsCombining(ucs))
|
||||
return 0;
|
||||
|
||||
if (IsFullWidth(ucs))
|
||||
return 2;
|
||||
|
||||
return 1;
|
||||
}
|
||||
|
||||
// From UTF8 encoded string |input|, eat in between 1 and 4 byte representing
|
||||
// one codepoint. Put the codepoint into |ucs|. Start at |start| and update
|
||||
// |end| to represent the beginning of the next byte to eat for consecutive
|
||||
// executions.
|
||||
bool EatCodePoint(const std::string& input,
|
||||
size_t start,
|
||||
size_t* end,
|
||||
uint32_t* ucs) {
|
||||
if (start >= input.size()) {
|
||||
*end = start + 1;
|
||||
return false;
|
||||
}
|
||||
uint8_t byte_1 = input[start];
|
||||
|
||||
// 1 byte string.
|
||||
if ((byte_1 & 0b1000'0000) == 0b0000'0000) {
|
||||
*ucs = byte_1 & 0b0111'1111;
|
||||
*end = start + 1;
|
||||
return true;
|
||||
}
|
||||
|
||||
// 2 byte string.
|
||||
if ((byte_1 & 0b1110'0000) == 0b1100'0000 && start + 1 < input.size()) {
|
||||
uint8_t byte_2 = input[start + 1];
|
||||
*ucs = 0;
|
||||
*ucs += byte_1 & 0b0001'1111;
|
||||
*ucs <<= 6;
|
||||
*ucs += byte_2 & 0b0011'1111;
|
||||
*end = start + 2;
|
||||
return true;
|
||||
}
|
||||
|
||||
// 3 byte string.
|
||||
if ((byte_1 & 0b1111'0000) == 0b1110'0000 && start + 2 < input.size()) {
|
||||
uint8_t byte_2 = input[start + 1];
|
||||
uint8_t byte_3 = input[start + 2];
|
||||
*ucs = 0;
|
||||
*ucs += byte_1 & 0b0000'1111;
|
||||
*ucs <<= 6;
|
||||
*ucs += byte_2 & 0b0011'1111;
|
||||
*ucs <<= 6;
|
||||
*ucs += byte_3 & 0b0011'1111;
|
||||
*end = start + 3;
|
||||
return true;
|
||||
}
|
||||
|
||||
// 4 byte string.
|
||||
if ((byte_1 & 0b1111'1000) == 0b1111'0000 && start + 3 < input.size()) {
|
||||
uint8_t byte_2 = input[start + 1];
|
||||
uint8_t byte_3 = input[start + 2];
|
||||
uint8_t byte_4 = input[start + 3];
|
||||
*ucs = 0;
|
||||
*ucs += byte_1 & 0b0000'0111;
|
||||
*ucs <<= 6;
|
||||
*ucs += byte_2 & 0b0011'1111;
|
||||
*ucs <<= 6;
|
||||
*ucs += byte_3 & 0b0011'1111;
|
||||
*ucs <<= 6;
|
||||
*ucs += byte_4 & 0b0011'1111;
|
||||
*end = start + 4;
|
||||
return true;
|
||||
}
|
||||
|
||||
*end = start + 1;
|
||||
return false;
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
namespace ftxui {
|
||||
int wchar_width(wchar_t ucs) {
|
||||
return codepoint_width(uint32_t(ucs));
|
||||
}
|
||||
|
||||
int wstring_width(const std::wstring& text) {
|
||||
int width = 0;
|
||||
|
||||
for (const wchar_t& it : text) {
|
||||
int w = wchar_width(it);
|
||||
if (w < 0)
|
||||
return -1;
|
||||
width += w;
|
||||
}
|
||||
return width;
|
||||
}
|
||||
|
||||
int string_width(const std::string& input) {
|
||||
int width = 0;
|
||||
size_t start = 0;
|
||||
while (start < input.size()) {
|
||||
uint32_t codepoint = 0;
|
||||
if (!EatCodePoint(input, start, &start, &codepoint))
|
||||
continue;
|
||||
|
||||
if (IsControl(codepoint))
|
||||
continue;
|
||||
|
||||
if (IsCombining(codepoint))
|
||||
continue;
|
||||
|
||||
if (IsFullWidth(codepoint)) {
|
||||
width += 2;
|
||||
continue;
|
||||
}
|
||||
|
||||
width += 1;
|
||||
}
|
||||
return width;
|
||||
}
|
||||
|
||||
std::vector<std::string> Utf8ToGlyphs(const std::string& input) {
|
||||
std::vector<std::string> out;
|
||||
std::string current;
|
||||
out.reserve(input.size());
|
||||
size_t start = 0;
|
||||
size_t end = 0;
|
||||
while (start < input.size()) {
|
||||
uint32_t codepoint;
|
||||
if (!EatCodePoint(input, start, &end, &codepoint)) {
|
||||
start = end;
|
||||
continue;
|
||||
}
|
||||
|
||||
std::string append = input.substr(start, end - start);
|
||||
start = end;
|
||||
|
||||
// Ignore control characters.
|
||||
if (IsControl(codepoint))
|
||||
continue;
|
||||
|
||||
// Combining characters are put with the previous glyph they are modifying.
|
||||
if (IsCombining(codepoint)) {
|
||||
if (out.size() != 0)
|
||||
out.back() += append;
|
||||
continue;
|
||||
}
|
||||
|
||||
// Fullwidth characters take two cells. The second is made of the empty
|
||||
// string to reserve the space the first is taking.
|
||||
if (IsFullWidth(codepoint)) {
|
||||
out.push_back(append);
|
||||
out.push_back("");
|
||||
continue;
|
||||
}
|
||||
|
||||
// Normal characters:
|
||||
out.push_back(append);
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
#ifdef _MSC_VER
|
||||
#pragma warning(push)
|
||||
#pragma warning(disable : 4996) // codecvt_utf8_utf16 is deprecated
|
||||
|
||||
47
src/ftxui/screen/string_test.cpp
Normal file
47
src/ftxui/screen/string_test.cpp
Normal file
@@ -0,0 +1,47 @@
|
||||
#include <gtest/gtest-message.h> // for Message
|
||||
#include <gtest/gtest-test-part.h> // for TestPartResult, SuiteApiResolver, TestFactoryImpl
|
||||
#include <string> // for allocator, string
|
||||
|
||||
#include "ftxui/screen/string.hpp"
|
||||
#include "gtest/gtest_pred_impl.h" // for EXPECT_EQ, Test, TEST
|
||||
|
||||
using namespace ftxui;
|
||||
|
||||
TEST(StringTest, StringWidth) {
|
||||
// Basic:
|
||||
EXPECT_EQ(0, string_width(""));
|
||||
EXPECT_EQ(1, string_width("a"));
|
||||
EXPECT_EQ(2, string_width("ab"));
|
||||
// Fullwidth glyphs:
|
||||
EXPECT_EQ(2, string_width("测"));
|
||||
EXPECT_EQ(4, string_width("测试"));
|
||||
// Combining characters:
|
||||
EXPECT_EQ(1, string_width("ā"));
|
||||
EXPECT_EQ(1, string_width("a⃒"));
|
||||
EXPECT_EQ(1, string_width("a̗"));
|
||||
// Control characters:
|
||||
EXPECT_EQ(0, string_width("\1"));
|
||||
EXPECT_EQ(2, string_width("a\1a"));
|
||||
}
|
||||
|
||||
TEST(StringTest, Utf8ToGlyphs) {
|
||||
using T = std::vector<std::string>;
|
||||
// Basic:
|
||||
EXPECT_EQ(Utf8ToGlyphs(""), T({}));
|
||||
EXPECT_EQ(Utf8ToGlyphs("a"), T({"a"}));
|
||||
EXPECT_EQ(Utf8ToGlyphs("ab"), T({"a", "b"}));
|
||||
// Fullwidth glyphs:
|
||||
EXPECT_EQ(Utf8ToGlyphs("测"), T({"测", ""}));
|
||||
EXPECT_EQ(Utf8ToGlyphs("测试"), T({"测", "", "试", ""}));
|
||||
// Combining characters:
|
||||
EXPECT_EQ(Utf8ToGlyphs("ā"), T({"ā"}));
|
||||
EXPECT_EQ(Utf8ToGlyphs("a⃒"), T({"a⃒"}));
|
||||
EXPECT_EQ(Utf8ToGlyphs("a̗"), T({"a̗"}));
|
||||
// Control characters:
|
||||
EXPECT_EQ(Utf8ToGlyphs("\1"), T({}));
|
||||
EXPECT_EQ(Utf8ToGlyphs("a\1a"), T({"a", "a"}));
|
||||
}
|
||||
|
||||
// Copyright 2020 Arthur Sonzogni. All rights reserved.
|
||||
// Use of this source code is governed by the MIT license that can be found in
|
||||
// the LICENSE file.
|
||||
@@ -1,317 +1,4 @@
|
||||
/*
|
||||
* This is an implementation of wcwidth() and wcswidth() (defined in
|
||||
* IEEE Std 1002.1-2001) for Unicode.
|
||||
*
|
||||
* http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html
|
||||
* http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html
|
||||
*
|
||||
* In fixed-width output devices, Latin characters all occupy a single
|
||||
* "cell" position of equal width, whereas ideographic CJK characters
|
||||
* occupy two such cells. Interoperability between terminal-line
|
||||
* applications and (teletype-style) character terminals using the
|
||||
* UTF-8 encoding requires agreement on which character should advance
|
||||
* the cursor by how many cell positions. No established formal
|
||||
* standards exist at present on which Unicode character shall occupy
|
||||
* how many cell positions on character terminals. These routines are
|
||||
* a first attempt of defining such behavior based on simple rules
|
||||
* applied to data provided by the Unicode Consortium.
|
||||
*
|
||||
* For some graphical characters, the Unicode standard explicitly
|
||||
* defines a character-cell width via the definition of the East Asian
|
||||
* FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes.
|
||||
* In all these cases, there is no ambiguity about which width a
|
||||
* terminal shall use. For characters in the East Asian Ambiguous (A)
|
||||
* class, the width choice depends purely on a preference of backward
|
||||
* compatibility with either historic CJK or Western practice.
|
||||
* Choosing single-width for these characters is easy to justify as
|
||||
* the appropriate long-term solution, as the CJK practice of
|
||||
* displaying these characters as double-width comes from historic
|
||||
* implementation simplicity (8-bit encoded characters were displayed
|
||||
* single-width and 16-bit ones double-width, even for Greek,
|
||||
* Cyrillic, etc.) and not any typographic considerations.
|
||||
*
|
||||
* Much less clear is the choice of width for the Not East Asian
|
||||
* (Neutral) class. Existing practice does not dictate a width for any
|
||||
* of these characters. It would nevertheless make sense
|
||||
* typographically to allocate two character cells to characters such
|
||||
* as for instance EM SPACE or VOLUME INTEGRAL, which cannot be
|
||||
* represented adequately with a single-width glyph. The following
|
||||
* routines at present merely assign a single-cell width to all
|
||||
* neutral characters, in the interest of simplicity. This is not
|
||||
* entirely satisfactory and should be reconsidered before
|
||||
* establishing a formal standard in this area. At the moment, the
|
||||
* decision which Not East Asian (Neutral) characters should be
|
||||
* represented by double-width glyphs cannot yet be answered by
|
||||
* applying a simple rule from the Unicode database content. Setting
|
||||
* up a proper standard for the behavior of UTF-8 character terminals
|
||||
* will require a careful analysis not only of each Unicode character,
|
||||
* but also of each presentation form, something the author of these
|
||||
* routines has avoided to do so far.
|
||||
*
|
||||
* http://www.unicode.org/unicode/reports/tr11/
|
||||
*
|
||||
* Markus Kuhn -- 2007-05-26 (Unicode 5.0)
|
||||
*
|
||||
* Permission to use, copy, modify, and distribute this software
|
||||
* for any purpose and without fee is hereby granted. The author
|
||||
* disclaims all warranties with regard to this software.
|
||||
*
|
||||
* Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "ftxui/screen/string.hpp"
|
||||
|
||||
namespace ftxui {
|
||||
|
||||
namespace {
|
||||
struct interval {
|
||||
char32_t first;
|
||||
char32_t last;
|
||||
};
|
||||
|
||||
/* auxiliary function for binary search in interval table */
|
||||
int bisearch(char32_t ucs, const struct interval* table, int max) {
|
||||
int min = 0;
|
||||
int mid;
|
||||
|
||||
if (ucs < table[0].first || ucs > table[max].last)
|
||||
return 0;
|
||||
while (max >= min) {
|
||||
mid = (min + max) / 2;
|
||||
if (ucs > table[mid].last)
|
||||
min = mid + 1;
|
||||
else if (ucs < table[mid].first)
|
||||
max = mid - 1;
|
||||
else
|
||||
return 1;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
} // namespace
|
||||
|
||||
/* The following two functions define the column width of an ISO 10646
|
||||
* character as follows:
|
||||
*
|
||||
* - The null character (U+0000) has a column width of 0.
|
||||
*
|
||||
* - Other C0/C1 control characters and DEL will lead to a return
|
||||
* value of -1.
|
||||
*
|
||||
* - Non-spacing and enclosing combining characters (general
|
||||
* category code Mn or Me in the Unicode database) have a
|
||||
* column width of 0.
|
||||
*
|
||||
* - SOFT HYPHEN (U+00AD) has a column width of 1.
|
||||
*
|
||||
* - Other format characters (general category code Cf in the Unicode
|
||||
* database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
|
||||
*
|
||||
* - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
|
||||
* have a column width of 0.
|
||||
*
|
||||
* - Spacing characters in the East Asian Wide (W) or East Asian
|
||||
* Full-width (F) category as defined in Unicode Technical
|
||||
* Report #11 have a column width of 2.
|
||||
*
|
||||
* - All remaining characters (including all printable
|
||||
* ISO 8859-1 and WGL4 characters, Unicode control characters,
|
||||
* etc.) have a column width of 1.
|
||||
*
|
||||
* This implementation assumes that char32_t characters are encoded
|
||||
* in ISO 10646.
|
||||
*/
|
||||
|
||||
int wchar_width(char32_t ucs) {
|
||||
/* sorted list of non-overlapping intervals of non-spacing characters */
|
||||
/* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
|
||||
static const struct interval combining[] = {
|
||||
{0x0300, 0x036F}, {0x0483, 0x0486}, {0x0488, 0x0489},
|
||||
{0x0591, 0x05BD}, {0x05BF, 0x05BF}, {0x05C1, 0x05C2},
|
||||
{0x05C4, 0x05C5}, {0x05C7, 0x05C7}, {0x0600, 0x0603},
|
||||
{0x0610, 0x0615}, {0x064B, 0x065E}, {0x0670, 0x0670},
|
||||
{0x06D6, 0x06E4}, {0x06E7, 0x06E8}, {0x06EA, 0x06ED},
|
||||
{0x070F, 0x070F}, {0x0711, 0x0711}, {0x0730, 0x074A},
|
||||
{0x07A6, 0x07B0}, {0x07EB, 0x07F3}, {0x0901, 0x0902},
|
||||
{0x093C, 0x093C}, {0x0941, 0x0948}, {0x094D, 0x094D},
|
||||
{0x0951, 0x0954}, {0x0962, 0x0963}, {0x0981, 0x0981},
|
||||
{0x09BC, 0x09BC}, {0x09C1, 0x09C4}, {0x09CD, 0x09CD},
|
||||
{0x09E2, 0x09E3}, {0x0A01, 0x0A02}, {0x0A3C, 0x0A3C},
|
||||
{0x0A41, 0x0A42}, {0x0A47, 0x0A48}, {0x0A4B, 0x0A4D},
|
||||
{0x0A70, 0x0A71}, {0x0A81, 0x0A82}, {0x0ABC, 0x0ABC},
|
||||
{0x0AC1, 0x0AC5}, {0x0AC7, 0x0AC8}, {0x0ACD, 0x0ACD},
|
||||
{0x0AE2, 0x0AE3}, {0x0B01, 0x0B01}, {0x0B3C, 0x0B3C},
|
||||
{0x0B3F, 0x0B3F}, {0x0B41, 0x0B43}, {0x0B4D, 0x0B4D},
|
||||
{0x0B56, 0x0B56}, {0x0B82, 0x0B82}, {0x0BC0, 0x0BC0},
|
||||
{0x0BCD, 0x0BCD}, {0x0C3E, 0x0C40}, {0x0C46, 0x0C48},
|
||||
{0x0C4A, 0x0C4D}, {0x0C55, 0x0C56}, {0x0CBC, 0x0CBC},
|
||||
{0x0CBF, 0x0CBF}, {0x0CC6, 0x0CC6}, {0x0CCC, 0x0CCD},
|
||||
{0x0CE2, 0x0CE3}, {0x0D41, 0x0D43}, {0x0D4D, 0x0D4D},
|
||||
{0x0DCA, 0x0DCA}, {0x0DD2, 0x0DD4}, {0x0DD6, 0x0DD6},
|
||||
{0x0E31, 0x0E31}, {0x0E34, 0x0E3A}, {0x0E47, 0x0E4E},
|
||||
{0x0EB1, 0x0EB1}, {0x0EB4, 0x0EB9}, {0x0EBB, 0x0EBC},
|
||||
{0x0EC8, 0x0ECD}, {0x0F18, 0x0F19}, {0x0F35, 0x0F35},
|
||||
{0x0F37, 0x0F37}, {0x0F39, 0x0F39}, {0x0F71, 0x0F7E},
|
||||
{0x0F80, 0x0F84}, {0x0F86, 0x0F87}, {0x0F90, 0x0F97},
|
||||
{0x0F99, 0x0FBC}, {0x0FC6, 0x0FC6}, {0x102D, 0x1030},
|
||||
{0x1032, 0x1032}, {0x1036, 0x1037}, {0x1039, 0x1039},
|
||||
{0x1058, 0x1059}, {0x1160, 0x11FF}, {0x135F, 0x135F},
|
||||
{0x1712, 0x1714}, {0x1732, 0x1734}, {0x1752, 0x1753},
|
||||
{0x1772, 0x1773}, {0x17B4, 0x17B5}, {0x17B7, 0x17BD},
|
||||
{0x17C6, 0x17C6}, {0x17C9, 0x17D3}, {0x17DD, 0x17DD},
|
||||
{0x180B, 0x180D}, {0x18A9, 0x18A9}, {0x1920, 0x1922},
|
||||
{0x1927, 0x1928}, {0x1932, 0x1932}, {0x1939, 0x193B},
|
||||
{0x1A17, 0x1A18}, {0x1B00, 0x1B03}, {0x1B34, 0x1B34},
|
||||
{0x1B36, 0x1B3A}, {0x1B3C, 0x1B3C}, {0x1B42, 0x1B42},
|
||||
{0x1B6B, 0x1B73}, {0x1DC0, 0x1DCA}, {0x1DFE, 0x1DFF},
|
||||
{0x200B, 0x200F}, {0x202A, 0x202E}, {0x2060, 0x2063},
|
||||
{0x206A, 0x206F}, {0x20D0, 0x20EF}, {0x302A, 0x302F},
|
||||
{0x3099, 0x309A}, {0xA806, 0xA806}, {0xA80B, 0xA80B},
|
||||
{0xA825, 0xA826}, {0xFB1E, 0xFB1E}, {0xFE00, 0xFE0F},
|
||||
{0xFE20, 0xFE23}, {0xFEFF, 0xFEFF}, {0xFFF9, 0xFFFB},
|
||||
{0x10A01, 0x10A03}, {0x10A05, 0x10A06}, {0x10A0C, 0x10A0F},
|
||||
{0x10A38, 0x10A3A}, {0x10A3F, 0x10A3F}, {0x1D167, 0x1D169},
|
||||
{0x1D173, 0x1D182}, {0x1D185, 0x1D18B}, {0x1D1AA, 0x1D1AD},
|
||||
{0x1D242, 0x1D244}, {0xE0001, 0xE0001}, {0xE0020, 0xE007F},
|
||||
{0xE0100, 0xE01EF}};
|
||||
|
||||
/* test for 8-bit control characters */
|
||||
if (ucs == 0)
|
||||
return 0;
|
||||
if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
|
||||
return -1;
|
||||
|
||||
/* binary search in table of non-spacing characters */
|
||||
if (bisearch(ucs, combining, sizeof(combining) / sizeof(struct interval) - 1))
|
||||
return 0;
|
||||
|
||||
/* if we arrive here, ucs is not a combining or C0/C1 control character */
|
||||
|
||||
return 1 +
|
||||
(ucs >= 0x1100 &&
|
||||
(ucs <= 0x115f || /* Hangul Jamo init. consonants */
|
||||
ucs == 0x2329 || ucs == 0x232a ||
|
||||
(ucs >= 0x2e80 && ucs <= 0xa4cf && ucs != 0x303f) || /* CJK ... Yi */
|
||||
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
|
||||
(ucs >= 0xf900 &&
|
||||
ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
|
||||
(ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
|
||||
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
|
||||
(ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
|
||||
(ucs >= 0xffe0 && ucs <= 0xffe6) ||
|
||||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
|
||||
(ucs >= 0x30000 && ucs <= 0x3fffd)));
|
||||
}
|
||||
|
||||
/*
|
||||
* The following functions are the same as mk_wcwidth() and
|
||||
* mk_wcswidth(), except that spacing characters in the East Asian
|
||||
* Ambiguous (A) category as defined in Unicode Technical Report #11
|
||||
* have a column width of 2. This variant might be useful for users of
|
||||
* CJK legacy encodings who want to migrate to UCS without changing
|
||||
* the traditional terminal character-width behaviour. It is not
|
||||
* otherwise recommended for general use.
|
||||
*/
|
||||
int wchar_width_cjk(char32_t ucs) {
|
||||
/* sorted list of non-overlapping intervals of East Asian Ambiguous
|
||||
* characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
|
||||
static const struct interval ambiguous[] = {
|
||||
{0x00A1, 0x00A1}, {0x00A4, 0x00A4}, {0x00A7, 0x00A8},
|
||||
{0x00AA, 0x00AA}, {0x00AE, 0x00AE}, {0x00B0, 0x00B4},
|
||||
{0x00B6, 0x00BA}, {0x00BC, 0x00BF}, {0x00C6, 0x00C6},
|
||||
{0x00D0, 0x00D0}, {0x00D7, 0x00D8}, {0x00DE, 0x00E1},
|
||||
{0x00E6, 0x00E6}, {0x00E8, 0x00EA}, {0x00EC, 0x00ED},
|
||||
{0x00F0, 0x00F0}, {0x00F2, 0x00F3}, {0x00F7, 0x00FA},
|
||||
{0x00FC, 0x00FC}, {0x00FE, 0x00FE}, {0x0101, 0x0101},
|
||||
{0x0111, 0x0111}, {0x0113, 0x0113}, {0x011B, 0x011B},
|
||||
{0x0126, 0x0127}, {0x012B, 0x012B}, {0x0131, 0x0133},
|
||||
{0x0138, 0x0138}, {0x013F, 0x0142}, {0x0144, 0x0144},
|
||||
{0x0148, 0x014B}, {0x014D, 0x014D}, {0x0152, 0x0153},
|
||||
{0x0166, 0x0167}, {0x016B, 0x016B}, {0x01CE, 0x01CE},
|
||||
{0x01D0, 0x01D0}, {0x01D2, 0x01D2}, {0x01D4, 0x01D4},
|
||||
{0x01D6, 0x01D6}, {0x01D8, 0x01D8}, {0x01DA, 0x01DA},
|
||||
{0x01DC, 0x01DC}, {0x0251, 0x0251}, {0x0261, 0x0261},
|
||||
{0x02C4, 0x02C4}, {0x02C7, 0x02C7}, {0x02C9, 0x02CB},
|
||||
{0x02CD, 0x02CD}, {0x02D0, 0x02D0}, {0x02D8, 0x02DB},
|
||||
{0x02DD, 0x02DD}, {0x02DF, 0x02DF}, {0x0391, 0x03A1},
|
||||
{0x03A3, 0x03A9}, {0x03B1, 0x03C1}, {0x03C3, 0x03C9},
|
||||
{0x0401, 0x0401}, {0x0410, 0x044F}, {0x0451, 0x0451},
|
||||
{0x2010, 0x2010}, {0x2013, 0x2016}, {0x2018, 0x2019},
|
||||
{0x201C, 0x201D}, {0x2020, 0x2022}, {0x2024, 0x2027},
|
||||
{0x2030, 0x2030}, {0x2032, 0x2033}, {0x2035, 0x2035},
|
||||
{0x203B, 0x203B}, {0x203E, 0x203E}, {0x2074, 0x2074},
|
||||
{0x207F, 0x207F}, {0x2081, 0x2084}, {0x20AC, 0x20AC},
|
||||
{0x2103, 0x2103}, {0x2105, 0x2105}, {0x2109, 0x2109},
|
||||
{0x2113, 0x2113}, {0x2116, 0x2116}, {0x2121, 0x2122},
|
||||
{0x2126, 0x2126}, {0x212B, 0x212B}, {0x2153, 0x2154},
|
||||
{0x215B, 0x215E}, {0x2160, 0x216B}, {0x2170, 0x2179},
|
||||
{0x2190, 0x2199}, {0x21B8, 0x21B9}, {0x21D2, 0x21D2},
|
||||
{0x21D4, 0x21D4}, {0x21E7, 0x21E7}, {0x2200, 0x2200},
|
||||
{0x2202, 0x2203}, {0x2207, 0x2208}, {0x220B, 0x220B},
|
||||
{0x220F, 0x220F}, {0x2211, 0x2211}, {0x2215, 0x2215},
|
||||
{0x221A, 0x221A}, {0x221D, 0x2220}, {0x2223, 0x2223},
|
||||
{0x2225, 0x2225}, {0x2227, 0x222C}, {0x222E, 0x222E},
|
||||
{0x2234, 0x2237}, {0x223C, 0x223D}, {0x2248, 0x2248},
|
||||
{0x224C, 0x224C}, {0x2252, 0x2252}, {0x2260, 0x2261},
|
||||
{0x2264, 0x2267}, {0x226A, 0x226B}, {0x226E, 0x226F},
|
||||
{0x2282, 0x2283}, {0x2286, 0x2287}, {0x2295, 0x2295},
|
||||
{0x2299, 0x2299}, {0x22A5, 0x22A5}, {0x22BF, 0x22BF},
|
||||
{0x2312, 0x2312}, {0x2460, 0x24E9}, {0x24EB, 0x254B},
|
||||
{0x2550, 0x2573}, {0x2580, 0x258F}, {0x2592, 0x2595},
|
||||
{0x25A0, 0x25A1}, {0x25A3, 0x25A9}, {0x25B2, 0x25B3},
|
||||
{0x25B6, 0x25B7}, {0x25BC, 0x25BD}, {0x25C0, 0x25C1},
|
||||
{0x25C6, 0x25C8}, {0x25CB, 0x25CB}, {0x25CE, 0x25D1},
|
||||
{0x25E2, 0x25E5}, {0x25EF, 0x25EF}, {0x2605, 0x2606},
|
||||
{0x2609, 0x2609}, {0x260E, 0x260F}, {0x2614, 0x2615},
|
||||
{0x261C, 0x261C}, {0x261E, 0x261E}, {0x2640, 0x2640},
|
||||
{0x2642, 0x2642}, {0x2660, 0x2661}, {0x2663, 0x2665},
|
||||
{0x2667, 0x266A}, {0x266C, 0x266D}, {0x266F, 0x266F},
|
||||
{0x273D, 0x273D}, {0x2776, 0x277F}, {0xE000, 0xF8FF},
|
||||
{0xFFFD, 0xFFFD}, {0xF0000, 0xFFFFD}, {0x100000, 0x10FFFD}};
|
||||
|
||||
/* binary search in table of non-spacing characters */
|
||||
if (bisearch(ucs, ambiguous, sizeof(ambiguous) / sizeof(struct interval) - 1))
|
||||
return 2;
|
||||
|
||||
return wchar_width(ucs);
|
||||
}
|
||||
|
||||
int wchar_width(wchar_t ucs) {
|
||||
return wchar_width(char32_t(ucs));
|
||||
}
|
||||
|
||||
int wchar_width_cjk(wchar_t ucs) {
|
||||
return wchar_width_cjk(char32_t(ucs));
|
||||
}
|
||||
|
||||
int wstring_width(const std::wstring& text) {
|
||||
int width = 0;
|
||||
|
||||
for (const wchar_t& it : text) {
|
||||
int w = wchar_width(it);
|
||||
if (w < 0)
|
||||
return -1;
|
||||
width += w;
|
||||
}
|
||||
return width;
|
||||
}
|
||||
|
||||
int wstring_width_cjk(const std::wstring& text) {
|
||||
int width = 0;
|
||||
|
||||
for (const wchar_t& it : text) {
|
||||
int w = wchar_width_cjk(it);
|
||||
if (w < 0)
|
||||
return -1;
|
||||
width += w;
|
||||
}
|
||||
return width;
|
||||
}
|
||||
|
||||
} // namespace ftxui
|
||||
|
||||
// Copyright 2020 Arthur Sonzogni. All rights reserved.
|
||||
// Copyright 2021 Arthur Sonzogni. All rights reserved.
|
||||
// Use of this source code is governed by the MIT license that can be found in
|
||||
// the LICENSE file.
|
||||
|
||||
Reference in New Issue
Block a user