From 0c98da2b108d62bb4abebd8ea9d6475bcaa7d56e Mon Sep 17 00:00:00 2001 From: skimo Date: Fri, 1 Sep 2000 11:31:13 +0000 Subject: [PATCH] Display single column Unicode characters in one column. All the Unicode handling ignores locale settings for now. --- common/conv.h | 17 ++++--- common/wcwidth.c | 130 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ dist/configure.in | 1 + gtk/gtkviscreen.c | 3 +- vi/vs_line.c | 4 +- 5 files changed, 146 insertions(+), 9 deletions(-) create mode 100644 common/wcwidth.c diff --git a/common/conv.h b/common/conv.h index 270056f3..76b11c21 100644 --- a/common/conv.h +++ b/common/conv.h @@ -1,9 +1,3 @@ -/* temporary assumption */ -#define CHAR_WIDTH(sp, ch) \ - ((UCHAR_T)(ch) > 255) ? 2 : 1 -#define KEY_COL(sp, ch) \ - (CHAR_WIDTH(sp, ch) > 1 ? CHAR_WIDTH(sp, ch) : KEY_LEN(sp,ch)) - #define F_GB 'A' #define INT9494(f,r,c) ((f) << 16) | ((r) << 8) | (c) @@ -14,6 +8,17 @@ #define INT9494R(c) ((c) >> 8) & 0x7F #define INT9494C(c) (c) & 0x7F #define INTILL(c) (1 << 23) | (c) +#ifdef USE_WIDECHAR +#define INTISWIDE(c) (!!(c >> 8)) +#define CHAR_WIDTH(sp, ch) \ + (INTISUCS(ch) && ucswidth(ch) > 0 ? ucswidth(ch) : INTISWIDE(ch) ? 2 : 1) +#else +#define INTISWIDE(c) 0 +#define CHAR_WIDTH(sp, ch) 1 +#endif + +#define KEY_COL(sp, ch) \ + (INTISWIDE(ch) ? CHAR_WIDTH(sp, ch) : KEY_LEN(sp,ch)) struct _conv { void *buffer; diff --git a/common/wcwidth.c b/common/wcwidth.c new file mode 100644 index 00000000..46db474a --- /dev/null +++ b/common/wcwidth.c @@ -0,0 +1,130 @@ +/* + * This is an implementation of wcwidth() and wcswidth() as defined in + * "The Single UNIX Specification, Version 2, The Open Group, 1997" + * + * + * Markus Kuhn -- 2000-02-08 -- public domain + */ + +#include + +/* These 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. + * + * - Spacing characters in the East Asian Wide (W) or East Asian + * FullWidth (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 ucswidth(wchar_t ucs) +{ + /* sorted list of non-overlapping intervals of non-spacing characters */ + static const struct interval { + unsigned short first; + unsigned short last; + } combining[] = { + { 0x0300, 0x034E }, { 0x0360, 0x0362 }, { 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 }, + { 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 }, { 0x17B7, 0x17BD }, + { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x18A9, 0x18A9 }, + { 0x20D0, 0x20E3 }, { 0x302A, 0x302F }, { 0x3099, 0x309A }, + { 0xFB1E, 0xFB1E }, { 0xFE20, 0xFE23 } + }; + int min = 0; + int max = sizeof(combining) / sizeof(struct interval) - 1; + int mid; + + /* test for 8-bit control characters */ + if (ucs == 0) + return 0; + if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0)) + return -1; + + /* first quick check for Latin-1 etc. characters */ + if (ucs < combining[0].first) + return 1; + + /* binary search in table of non-spacing characters */ + while (max >= min) { + mid = (min + max) / 2; + if (combining[mid].last < ucs) + min = mid + 1; + else if (combining[mid].first > ucs) + max = mid - 1; + else if (combining[mid].first <= ucs && combining[mid].last >= ucs) + return 0; + } + + /* if we arrive here, ucs is not a combining or C0/C1 control character */ + + /* fast test for majority of non-wide scripts */ + if (ucs < 0x1100) + return 1; + + return 1 + + ((ucs >= 0x1100 && ucs <= 0x115f) || /* Hangul Jamo */ + (ucs >= 0x2e80 && ucs <= 0xa4cf && (ucs & ~0x0011) != 0x300a && + 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 <= 0xff5f) || /* Fullwidth Forms */ + (ucs >= 0xffe0 && ucs <= 0xffe6)); +} + + +#if 0 +int wcswidth(const wchar_t *pwcs, size_t n) +{ + int w, width = 0; + + for (;*pwcs && n-- > 0; pwcs++) + if ((w = wcwidth(*pwcs)) < 0) + return -1; + else + width += w; + + return width; +} +#endif diff --git a/dist/configure.in b/dist/configure.in index 461ce3e8..4f87a7d0 100644 --- a/dist/configure.in +++ b/dist/configure.in @@ -214,6 +214,7 @@ AC_ARG_ENABLE(widechar, [vi_cv_widechar="yes"], [vi_cv_widechar="no"]) if test "$vi_cv_widechar" = "yes"; then AC_DEFINE(USE_WIDECHAR) + LIBOBJS="wcwidth.o $LIBOBJS" fi AC_MSG_RESULT($vi_cv_widechar) diff --git a/gtk/gtkviscreen.c b/gtk/gtkviscreen.c index 22225216..93d61c5a 100644 --- a/gtk/gtkviscreen.c +++ b/gtk/gtkviscreen.c @@ -683,7 +683,8 @@ draw_lines(GtkViScreen *vi, gint ymin, gint xmin, gint ymax, gint xmax) y < ymax; ++y, line += vi->cols) { for (x = 0, xpos = 0; xpos <= xmin; ++x) xpos += CHAR_WIDTH(NULL, *(line+x)); - xpos -= CHAR_WIDTH(NULL, *(line+--x)); + --x; + xpos -= CHAR_WIDTH(NULL, *(line+x)); for (; xpos < xmax; x+=len, xpos+= blen) { gchar inverse; inverse = Inverse(vi,y,x); diff --git a/vi/vs_line.c b/vi/vs_line.c index 0fa6e872..121d5565 100644 --- a/vi/vs_line.c +++ b/vi/vs_line.c @@ -10,7 +10,7 @@ #include "config.h" #ifndef lint -static const char sccsid[] = "$Id: vs_line.c,v 10.27 2000/08/27 09:49:42 skimo Exp $ (Berkeley) $Date: 2000/08/27 09:49:42 $"; +static const char sccsid[] = "$Id: vs_line.c,v 10.28 2000/09/01 11:31:15 skimo Exp $ (Berkeley) $Date: 2000/09/01 11:31:15 $"; #endif /* not lint */ #include @@ -420,7 +420,7 @@ display: else { if (cbp + chlen >= ecbp) FLUSH; - if (CHAR_WIDTH(sp, ch) > 1) + if (INTISWIDE(ch)) *cbp++ = ch; else for (kp = KEY_NAME(sp, ch) + offset_in_char; -- 2.11.4.GIT