diff options
author | behdad <behdad> | 2002-05-16 10:11:52 +0000 |
---|---|---|
committer | behdad <behdad> | 2002-05-16 10:11:52 +0000 |
commit | 73ea6f2a3f1b337a7c632c0854c4ca4e282ca200 (patch) | |
tree | bb696fddd629ab7e1b39dfcb3bb299e82f1cb137 | |
parent | 2a41c66718fb5973042730099609482b344d9863 (diff) |
Updated wcwidth.
-rw-r--r-- | ChangeLog | 5 | ||||
-rw-r--r-- | Makefile.am | 4 | ||||
-rw-r--r-- | fribidi_wcwidth.c | 333 | ||||
-rw-r--r-- | fribidi_wcwidth.i | 9 |
4 files changed, 204 insertions, 147 deletions
@@ -1,3 +1,8 @@ +2002-05-16 Behdad Esfahbod <fribidi@behdad.org> + * fribidi_wcwidth.c: Updated to latest source of 2002-05-08. + * fribidi_wcwidth.i: Added, fribidi_wcwidth.c includes this to reduces + changes needed in fribidi_wcwidth.c. + 2002-05-04 Behdad Esfahbod <fribidi@behdad.org> * fribidi_wcwidth.c: Updated to latest source of 2002-05-03. diff --git a/Makefile.am b/Makefile.am index af47f2e..af1b186 100644 --- a/Makefile.am +++ b/Makefile.am @@ -83,6 +83,9 @@ UNIDATA_FILES = \ unidata/UnicodeData.txt \ unidata/BidiMirroring.txt +OTHER_FILES = \ + fribidi_wcwidth.i + EXTRA_HEADERS = \ packtab.h \ $(GETOPT_HDR) @@ -99,6 +102,7 @@ EXTRA_DIST = \ $(TEST_FILES) \ $(TABLE_FILES) \ $(UNIDATA_FILES) \ + $(OTHER_FILES) \ $(EXTRA_HEADERS) fribidi_benchmark_SOURCES = fribidi_benchmark.c $(GETOPT_SRC) diff --git a/fribidi_wcwidth.c b/fribidi_wcwidth.c index 869aa6e..eec17a4 100644 --- a/fribidi_wcwidth.c +++ b/fribidi_wcwidth.c @@ -1,55 +1,93 @@ /* - * This is an implementation of wcwidth() and wcswidth() as defined in - * IEEE Std 1002.1-2001. + * 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 * - * Markus Kuhn -- 2002-05-03 (Unicode 3.2) + * 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 -- 2002-05-08 (Unicode 3.2) + * * 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 + * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c */ -/* Modified by Behdad Esfahbod <behdad@bamdad.org> to use fribidi types*/ - -#include "fribidi.h" +#include "fribidi_wcwidth.i" -struct interval -{ +struct interval { int first; int last; }; /* auxiliary function for binary search in interval table */ -static int -bisearch (FriBidiChar ucs, const struct interval *table, int max) -{ +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; - } + 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 functions define the column width of an ISO 10646 +/* 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. @@ -68,61 +106,60 @@ bisearch (FriBidiChar ucs, const struct interval *table, int max) * have a column width of 0. * * - Spacing characters in the East Asian Wide (W) or East Asian - * FullWidth (F) category as defined in Unicode Technical + * 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 FriBidiChar characters are encoded + * This implementation assumes that wchar_t characters are encoded * in ISO 10646. */ -int -fribidi_wcwidth (FriBidiChar ucs) +int mk_wcwidth(wchar_t ucs) { /* sorted list of non-overlapping intervals of non-spacing characters */ /* generated with "uniset +cat=Me +cat=Mn +cat=Cf +1160-11FF +200B c" */ static const struct interval combining[] = { - {0x0300, 0x034F}, {0x0360, 0x036F}, {0x0483, 0x0486}, - {0x0488, 0x0489}, {0x0591, 0x05A1}, {0x05A3, 0x05B9}, - {0x05BB, 0x05BD}, {0x05BF, 0x05BF}, {0x05C1, 0x05C2}, - {0x05C4, 0x05C4}, {0x064B, 0x0655}, {0x0670, 0x0670}, - {0x06D6, 0x06E4}, {0x06E7, 0x06E8}, {0x06EA, 0x06ED}, - {0x070F, 0x070F}, {0x0711, 0x0711}, {0x0730, 0x074A}, - {0x07A6, 0x07B0}, {0x0901, 0x0902}, {0x093C, 0x093C}, - {0x0941, 0x0948}, {0x094D, 0x094D}, {0x0951, 0x0954}, - {0x0962, 0x0963}, {0x0981, 0x0981}, {0x09BC, 0x09BC}, - {0x09C1, 0x09C4}, {0x09CD, 0x09CD}, {0x09E2, 0x09E3}, - {0x0A02, 0x0A02}, {0x0A3C, 0x0A3C}, {0x0A41, 0x0A42}, - {0x0A47, 0x0A48}, {0x0A4B, 0x0A4D}, {0x0A70, 0x0A71}, - {0x0A81, 0x0A82}, {0x0ABC, 0x0ABC}, {0x0AC1, 0x0AC5}, - {0x0AC7, 0x0AC8}, {0x0ACD, 0x0ACD}, {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}, - {0x0CBF, 0x0CBF}, {0x0CC6, 0x0CC6}, {0x0CCC, 0x0CCD}, - {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}, {0x1712, 0x1714}, {0x1732, 0x1734}, - {0x1752, 0x1753}, {0x1772, 0x1773}, {0x17B7, 0x17BD}, - {0x17C6, 0x17C6}, {0x17C9, 0x17D3}, {0x180B, 0x180E}, - {0x18A9, 0x18A9}, {0x200B, 0x200F}, {0x202A, 0x202E}, - {0x2060, 0x2063}, {0x206A, 0x206F}, {0x20D0, 0x20EA}, - {0x302A, 0x302F}, {0x3099, 0x309A}, {0xFB1E, 0xFB1E}, - {0xFE00, 0xFE0F}, {0xFE20, 0xFE23}, {0xFEFF, 0xFEFF}, - {0xFFF9, 0xFFFB}, {0x1D167, 0x1D169}, {0x1D173, 0x1D182}, - {0x1D185, 0x1D18B}, {0x1D1AA, 0x1D1AD}, {0xE0001, 0xE0001}, - {0xE0020, 0xE007F} + { 0x0300, 0x034F }, { 0x0360, 0x036F }, { 0x0483, 0x0486 }, + { 0x0488, 0x0489 }, { 0x0591, 0x05A1 }, { 0x05A3, 0x05B9 }, + { 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, + { 0x05C4, 0x05C4 }, { 0x064B, 0x0655 }, { 0x0670, 0x0670 }, + { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, + { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A }, + { 0x07A6, 0x07B0 }, { 0x0901, 0x0902 }, { 0x093C, 0x093C }, + { 0x0941, 0x0948 }, { 0x094D, 0x094D }, { 0x0951, 0x0954 }, + { 0x0962, 0x0963 }, { 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, + { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, + { 0x0A02, 0x0A02 }, { 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, + { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 }, + { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, + { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD }, { 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 }, + { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD }, + { 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 }, { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, + { 0x1752, 0x1753 }, { 0x1772, 0x1773 }, { 0x17B7, 0x17BD }, + { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x180B, 0x180E }, + { 0x18A9, 0x18A9 }, { 0x200B, 0x200F }, { 0x202A, 0x202E }, + { 0x2060, 0x2063 }, { 0x206A, 0x206F }, { 0x20D0, 0x20EA }, + { 0x302A, 0x302F }, { 0x3099, 0x309A }, { 0xFB1E, 0xFB1E }, + { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, + { 0xFFF9, 0xFFFB }, { 0x1D167, 0x1D169 }, { 0x1D173, 0x1D182 }, + { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD }, { 0xE0001, 0xE0001 }, + { 0xE0020, 0xE007F } }; /* test for 8-bit control characters */ @@ -132,30 +169,33 @@ fribidi_wcwidth (FriBidiChar ucs) return -1; /* binary search in table of non-spacing characters */ - if (bisearch (ucs, combining, - sizeof (combining) / sizeof (struct interval) - 1)) + 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 >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */ - (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */ - (ucs >= 0xffe0 && ucs <= 0xffe6) || - (ucs >= 0x20000 && ucs <= 0x2ffff))); + 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 >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */ + (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */ + (ucs >= 0xffe0 && ucs <= 0xffe6) || + (ucs >= 0x20000 && ucs <= 0x2ffff))); } -int -fribidi_wcswidth (const FriBidiChar *pwcs, FriBidiStrIndex n) +int mk_wcswidth(const wchar_t *pwcs, size_t n) { int w, width = 0; - for (; *pwcs && n-- > 0; pwcs++) - if ((w = fribidi_wcwidth (*pwcs)) < 0) + for (;*pwcs && n-- > 0; pwcs++) + if ((w = mk_wcwidth(*pwcs)) < 0) return -1; else width += w; @@ -165,88 +205,87 @@ fribidi_wcswidth (const FriBidiChar *pwcs, FriBidiStrIndex n) /* - * The following function is the same as wcwidth(), 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 experimental variant might be useful for users of CJK legacy - * encodings who want to migrate to UCS. It is not otherwise - * recommended for general use. + * The following functions are the same as mk_wcwidth() and + * mk_wcwidth_cjk(), 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. */ -static int -fribidi_wcwidth_cjk (FriBidiChar ucs) +static int mk_wcwidth_cjk(wchar_t ucs) { /* sorted list of non-overlapping intervals of East Asian Ambiguous * characters, generated with "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */ static const struct interval ambiguous[] = { - {0x00A1, 0x00A1}, {0x00A4, 0x00A4}, {0x00A7, 0x00A8}, - {0x00AA, 0x00AA}, {0x00AD, 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, 0x24FE}, - {0x2500, 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}, - {0x261C, 0x261C}, {0x261E, 0x261E}, {0x2640, 0x2640}, - {0x2642, 0x2642}, {0x2660, 0x2661}, {0x2663, 0x2665}, - {0x2667, 0x266A}, {0x266C, 0x266D}, {0x266F, 0x266F}, - {0x273D, 0x273D}, {0x2776, 0x277F}, {0xFFFD, 0xFFFD} + { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 }, + { 0x00AA, 0x00AA }, { 0x00AD, 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, 0x24FE }, + { 0x2500, 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 }, + { 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 }, + { 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 }, + { 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F }, + { 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xFFFD, 0xFFFD } }; /* binary search in table of non-spacing characters */ - if (bisearch (ucs, ambiguous, - sizeof (ambiguous) / sizeof (struct interval) - 1)) + if (bisearch(ucs, ambiguous, + sizeof(ambiguous) / sizeof(struct interval) - 1)) return 2; - return fribidi_wcwidth (ucs); + return mk_wcwidth(ucs); } -int -fribidi_wcswidth_cjk (const FriBidiChar *pwcs, FriBidiStrIndex n) +int mk_wcswidth_cjk(const wchar_t *pwcs, size_t n) { int w, width = 0; - for (; *pwcs && n-- > 0; pwcs++) - if ((w = fribidi_wcwidth_cjk (*pwcs)) < 0) + for (;*pwcs && n-- > 0; pwcs++) + if ((w = mk_wcwidth_cjk(*pwcs)) < 0) return -1; else width += w; diff --git a/fribidi_wcwidth.i b/fribidi_wcwidth.i new file mode 100644 index 0000000..6fc7b92 --- /dev/null +++ b/fribidi_wcwidth.i @@ -0,0 +1,9 @@ +#include "fribidi.h" + +#define mk_wcwidth fribidi_wcwidth +#define mk_wcswidth fribidi_wcswidth +#define mk_wcwidth_cjk fribidi_wcwidth_cjk +#define mk_wcswidth_cjk fribidi_wcswidth_cjk + +#define wchar_t FriBidiChar +#define size_t FriBidiStrIndex |