GothenburgBitFactory/taskwarrior
1
0
Fork 0
mirror of https://github.com/GothenburgBitFactory/taskwarrior.git synced 2025-07-07 20:06:36 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

libshared: Integrated utf8, wcwidth

Browse source
This commit is contained in:
Paul Beckingham 2016-06-25 17:52:20 -04:00
parent 446580d8dd
commit 43de419cdd
4 changed files with 4 additions and 556 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/CMakeLists.txt
View file

@ -35,14 +35,14 @@ add_library (task CLI2.cpp CLI2.h
rules.cpp rules.cpp
sort.cpp sort.cpp
text.cpp text.h text.cpp text.h
utf8.cpp utf8.h util.cpp util.h)
util.cpp util.h
wcwidth6.cpp)
add_library (libshared libshared/src/JSON.cpp libshared/src/JSON.h add_library (libshared libshared/src/JSON.cpp libshared/src/JSON.h
libshared/src/Pig.cpp libshared/src/Pig.h libshared/src/Pig.cpp libshared/src/Pig.h
libshared/src/RX.cpp libshared/src/RX.h libshared/src/RX.cpp libshared/src/RX.h
libshared/src/unicode.cpp libshared/src/unicode.h) libshared/src/unicode.cpp libshared/src/unicode.h
libshared/src/utf8.cpp libshared/src/utf8.h
libshared/src/wcwidth6.cpp)
add_executable (task_executable main.cpp) add_executable (task_executable main.cpp)
add_executable (calc_executable calc.cpp) add_executable (calc_executable calc.cpp)

296
src/utf8.cpp
View file

@ -1,296 +0,0 @@
////////////////////////////////////////////////////////////////////////////////
//
// Copyright 2013 - 2016, Paul Beckingham, Federico Hernandez.
//
// 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.
//
// http://www.opensource.org/licenses/mit-license.php
//
////////////////////////////////////////////////////////////////////////////////
#include <cmake.h>
#include <utf8.h>
#include <string>
////////////////////////////////////////////////////////////////////////////////
// Converts '0' -> 0
// '9' -> 9
// 'a'/'A' -> 10
// 'f'/'F' -> 15
#define XDIGIT(x) ((x) >= '0' && (x) <= '9' ? ((x) - '0') : \
(x) >= 'a' && (x) <= 'f' ? ((x) + 10 - 'a') : \
(x) >= 'A' && (x) <= 'F' ? ((x) + 10 - 'A') : 0)
////////////////////////////////////////////////////////////////////////////////
// Note: Assumes 4-digit hex codepoints:
// xxxx
// \uxxxx
// U+xxxx
unsigned int utf8_codepoint (const std::string& input)
{
unsigned int codepoint = 0;
int length = input.length ();
// U+xxxx, \uxxxx
if (length >= 6 &&
((input[0] == 'U' && input[1] == '+') ||
(input[0] == '\\' && input[1] == 'u')))
{
codepoint = XDIGIT (input[2]) << 12 |
XDIGIT (input[3]) << 8 |
XDIGIT (input[4]) << 4 |
XDIGIT (input[5]);
}
else if (length >= 4)
{
codepoint = XDIGIT (input[0]) << 12 |
XDIGIT (input[1]) << 8 |
XDIGIT (input[2]) << 4 |
XDIGIT (input[3]);
}
return codepoint;
}
////////////////////////////////////////////////////////////////////////////////
// Iterates along a UTF8 string.
// - argument i counts bytes advanced through the string
// - returns the next character
unsigned int utf8_next_char (const std::string& input, std::string::size_type& i)
{
if (input[i] == '\0')
return 0;
// How many bytes in the sequence?
int length = utf8_sequence (input[i]);
i += length;
// 0xxxxxxx -> 0xxxxxxx
if (length == 1)
return input[i - 1];
// 110yyyyy 10xxxxxx -> 00000yyy yyxxxxxx
if (length == 2)
return ((input[i - 2] & 0x1F) << 6) +
(input[i - 1] & 0x3F);
// 1110zzzz 10yyyyyy 10xxxxxx -> zzzzyyyy yyxxxxxx
if (length == 3)
return ((input[i - 3] & 0xF) << 12) +
((input[i - 2] & 0x3F) << 6) +
(input[i - 1] & 0x3F);
// 11110www 10zzzzzz 10yyyyyy 10xxxxxx -> 000wwwzz zzzzyyyy yyxxxxxx
if (length == 4)
return ((input[i - 4] & 0x7) << 18) +
((input[i - 3] & 0x3F) << 12) +
((input[i - 2] & 0x3F) << 6) +
(input[i - 1] & 0x3F);
// Default: pretend as though it's a single character.
// TODO Or should this throw?
return input[i - 1];
}
////////////////////////////////////////////////////////////////////////////////
// http://en.wikipedia.org/wiki/UTF-8
std::string utf8_character (unsigned int codepoint)
{
char sequence[5] {};
// 0xxxxxxx -> 0xxxxxxx
if (codepoint < 0x80)
{
sequence[0] = codepoint;
}
// 00000yyy yyxxxxxx -> 110yyyyy 10xxxxxx
else if (codepoint < 0x800)
{
sequence[0] = 0xC0 | (codepoint & 0x7C0) >> 6;
sequence[1] = 0x80 | (codepoint & 0x3F);
}
// zzzzyyyy yyxxxxxx -> 1110zzzz 10yyyyyy 10xxxxxx
else if (codepoint < 0x10000)
{
sequence[0] = 0xE0 | (codepoint & 0xF000) >> 12;
sequence[1] = 0x80 | (codepoint & 0xFC0) >> 6;
sequence[2] = 0x80 | (codepoint & 0x3F);
}
// 000wwwzz zzzzyyyy yyxxxxxx -> 11110www 10zzzzzz 10yyyyyy 10xxxxxx
else if (codepoint < 0x110000)
{
sequence[0] = 0xF0 | (codepoint & 0x1C0000) >> 18;
sequence[1] = 0x80 | (codepoint & 0x03F000) >> 12;
sequence[2] = 0x80 | (codepoint & 0x0FC0) >> 6;
sequence[3] = 0x80 | (codepoint & 0x3F);
}
return std::string (sequence);
}
////////////////////////////////////////////////////////////////////////////////
int utf8_sequence (unsigned int character)
{
if ((character & 0xE0) == 0xC0)
return 2;
if ((character & 0xF0) == 0xE0)
return 3;
if ((character & 0xF8) == 0xF0)
return 4;
return 1;
}
////////////////////////////////////////////////////////////////////////////////
// Length of a string in characters.
unsigned int utf8_length (const std::string& str)
{
int byteLength = str.length ();
int charLength = byteLength;
const char* data = str.data ();
// Decrement the number of bytes for each byte that matches 0b10??????
// this way only the first byte of any utf8 sequence is counted.
for (int i = 0; i < byteLength; i++)
{
// Extract the first two bits and check whether they are 10
if ((data[i] & 0xC0) == 0x80)
charLength--;
}
return charLength;
}
////////////////////////////////////////////////////////////////////////////////
// Width of a string in character cells.
unsigned int utf8_width (const std::string& str)
{
unsigned int length = 0;
std::string::size_type i = 0;
unsigned int c;
while ((c = utf8_next_char (str, i)))
{
// Control characters, and more especially newline characters, make
// mk_wcwidth() return -1. Ignore that, thereby "adding zero" to length.
// Since control characters are not displayed in reports, this is a valid
// choice.
int l = mk_wcwidth (c);
if (l != -1)
length += l;
}
return length;
}
////////////////////////////////////////////////////////////////////////////////
unsigned int utf8_text_length (const std::string& str)
{
int byteLength = str.length ();
int charLength = byteLength;
const char* data = str.data ();
bool in_color = false;
// Decrement the number of bytes for each byte that matches 0b10??????
// this way only the first byte of any utf8 sequence is counted.
for (int i = 0; i < byteLength; i++)
{
if (in_color)
{
if (data[i] == 'm')
in_color = false;
--charLength;
}
else
{
if (data[i] == 033)
{
in_color = true;
--charLength;
}
else
{
// Extract the first two bits and check whether they are 10
if ((data[i] & 0xC0) == 0x80)
--charLength;
}
}
}
return charLength;
}
////////////////////////////////////////////////////////////////////////////////
unsigned int utf8_text_width (const std::string& str)
{
bool in_color = false;
unsigned int length = 0;
std::string::size_type i = 0;
unsigned int c;
while ((c = utf8_next_char (str, i)))
{
if (in_color)
{
if (c == 'm')
in_color = false;
}
else if (c == 033)
{
in_color = true;
}
else
length += mk_wcwidth (c);
}
return length;
}
////////////////////////////////////////////////////////////////////////////////
const std::string utf8_substr (
const std::string& input,
unsigned int start,
unsigned int length /* = 0 */)
{
// Find the starting index.
std::string::size_type index_start = 0;
for (unsigned int i = 0; i < start; i++)
utf8_next_char (input, index_start);
std::string result;
if (length)
{
std::string::size_type index_end = index_start;
for (unsigned int i = 0; i < length; i++)
utf8_next_char (input, index_end);
result = input.substr (index_start, index_end - index_start);
}
else
result = input.substr (index_start);
return result;
}
////////////////////////////////////////////////////////////////////////////////

45
src/utf8.h
View file

@ -1,45 +0,0 @@
////////////////////////////////////////////////////////////////////////////////
//
// Copyright 2013 - 2016, Paul Beckingham, Federico Hernandez.
//
// 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.
//
// http://www.opensource.org/licenses/mit-license.php
//
////////////////////////////////////////////////////////////////////////////////
#ifndef INCLUDED_UTF8
#define INCLUDED_UTF8
#include <string>
unsigned int utf8_codepoint (const std::string&);
unsigned int utf8_next_char (const std::string&, std::string::size_type&);
std::string utf8_character (unsigned int);
int utf8_sequence (unsigned int);
unsigned int utf8_length (const std::string&);
unsigned int utf8_text_length (const std::string&);
unsigned int utf8_width (const std::string& str);
unsigned int utf8_text_width (const std::string&);
const std::string utf8_substr (const std::string&, unsigned int, unsigned int length = 0);
int mk_wcwidth (wchar_t);
#endif
////////////////////////////////////////////////////////////////////////////////

211
src/wcwidth6.cpp
View file

@ -1,211 +0,0 @@
/*
* 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 <cmake.h>
#include <wchar.h>
struct interval {
int first;
int last;
};
/* auxiliary function for binary search in interval table */
static int bisearch(wchar_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;
}
/* 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 wchar_t characters are encoded
* in ISO 10646.
*/
int mk_wcwidth(wchar_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)
#ifndef CYGWIN
||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
(ucs >= 0x30000 && ucs <= 0x3fffd)
#endif
)
);
}