2
===================================================================
3
RCS file: /schmorpforge/rxvt-unicode/src/Makefile.in,v
4
retrieving revision 1.100
5
diff -u -r1.100 Makefile.in
6
--- src/Makefile.in 26 Jun 2007 21:59:13 -0000 1.100
7
+++ src/Makefile.in 27 Jun 2007 11:08:25 -0000
9
command.o rxvtfont.o init.o logging.o main.o misc.o netdisp.o \
10
ptytty.o proxy.o screen.o scrollbar.o scrollbar-next.o scrollbar-rxvt.o \
11
scrollbar-xterm.o scrollbar-plain.o xdefaults.o xpm.o encoding.o \
12
- rxvttoolkit.o rxvtutil.o iom.o keyboard.o fdpass.o @PERL_O@
13
+ rxvttoolkit.o rxvtutil.o iom.o keyboard.o fdpass.o @PERL_O@ wcwidth.o
15
COMMON_DAEMON = rxvtdaemon.o
18
===================================================================
19
RCS file: /schmorpforge/rxvt-unicode/src/rxvt.h,v
20
retrieving revision 1.275
21
diff -u -r1.275 rxvt.h
22
--- src/rxvt.h 26 Jun 2007 00:40:19 -0000 1.275
23
+++ src/rxvt.h 27 Jun 2007 11:08:26 -0000
26
#define dLocal(type,name) type const name = this->name
28
+int mk_wcwidth(wchar_t c);
29
+int mk_wcswidth(const wchar_t *s, size_t n);
31
+#define wcwidth mk_wcwidth
32
+#define wcswidth mk_wcswidth
34
// for speed reasons, we assume that all codepoints 32 to 126 are
36
#define WCWIDTH(c) (IN_RANGE_INC (c, 0x20, 0x7e) ? 1 : wcwidth (c))
37
--- src/wcwidth.C 1970-01-01 01:00:00.000000000 +0100
38
+++ src/wcwidth.C 2007-06-14 13:11:38.000000000 +0200
41
+ * This is an implementation of wcwidth() and wcswidth() (defined in
42
+ * IEEE Std 1002.1-2001) for Unicode.
44
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html
45
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html
47
+ * In fixed-width output devices, Latin characters all occupy a single
48
+ * "cell" position of equal width, whereas ideographic CJK characters
49
+ * occupy two such cells. Interoperability between terminal-line
50
+ * applications and (teletype-style) character terminals using the
51
+ * UTF-8 encoding requires agreement on which character should advance
52
+ * the cursor by how many cell positions. No established formal
53
+ * standards exist at present on which Unicode character shall occupy
54
+ * how many cell positions on character terminals. These routines are
55
+ * a first attempt of defining such behavior based on simple rules
56
+ * applied to data provided by the Unicode Consortium.
58
+ * For some graphical characters, the Unicode standard explicitly
59
+ * defines a character-cell width via the definition of the East Asian
60
+ * FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes.
61
+ * In all these cases, there is no ambiguity about which width a
62
+ * terminal shall use. For characters in the East Asian Ambiguous (A)
63
+ * class, the width choice depends purely on a preference of backward
64
+ * compatibility with either historic CJK or Western practice.
65
+ * Choosing single-width for these characters is easy to justify as
66
+ * the appropriate long-term solution, as the CJK practice of
67
+ * displaying these characters as double-width comes from historic
68
+ * implementation simplicity (8-bit encoded characters were displayed
69
+ * single-width and 16-bit ones double-width, even for Greek,
70
+ * Cyrillic, etc.) and not any typographic considerations.
72
+ * Much less clear is the choice of width for the Not East Asian
73
+ * (Neutral) class. Existing practice does not dictate a width for any
74
+ * of these characters. It would nevertheless make sense
75
+ * typographically to allocate two character cells to characters such
76
+ * as for instance EM SPACE or VOLUME INTEGRAL, which cannot be
77
+ * represented adequately with a single-width glyph. The following
78
+ * routines at present merely assign a single-cell width to all
79
+ * neutral characters, in the interest of simplicity. This is not
80
+ * entirely satisfactory and should be reconsidered before
81
+ * establishing a formal standard in this area. At the moment, the
82
+ * decision which Not East Asian (Neutral) characters should be
83
+ * represented by double-width glyphs cannot yet be answered by
84
+ * applying a simple rule from the Unicode database content. Setting
85
+ * up a proper standard for the behavior of UTF-8 character terminals
86
+ * will require a careful analysis not only of each Unicode character,
87
+ * but also of each presentation form, something the author of these
88
+ * routines has avoided to do so far.
90
+ * http://www.unicode.org/unicode/reports/tr11/
92
+ * Markus Kuhn -- 2007-05-26 (Unicode 5.0)
94
+ * Permission to use, copy, modify, and distribute this software
95
+ * for any purpose and without fee is hereby granted. The author
96
+ * disclaims all warranties with regard to this software.
98
+ * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
108
+/* auxiliary function for binary search in interval table */
109
+static int bisearch(wchar_t ucs, const struct interval *table, int max) {
113
+ if (ucs < table[0].first || ucs > table[max].last)
115
+ while (max >= min) {
116
+ mid = (min + max) / 2;
117
+ if (ucs > table[mid].last)
119
+ else if (ucs < table[mid].first)
129
+/* The following two functions define the column width of an ISO 10646
130
+ * character as follows:
132
+ * - The null character (U+0000) has a column width of 0.
134
+ * - Other C0/C1 control characters and DEL will lead to a return
137
+ * - Non-spacing and enclosing combining characters (general
138
+ * category code Mn or Me in the Unicode database) have a
139
+ * column width of 0.
141
+ * - SOFT HYPHEN (U+00AD) has a column width of 1.
143
+ * - Other format characters (general category code Cf in the Unicode
144
+ * database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
146
+ * - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
147
+ * have a column width of 0.
149
+ * - Spacing characters in the East Asian Wide (W) or East Asian
150
+ * Full-width (F) category as defined in Unicode Technical
151
+ * Report #11 have a column width of 2.
153
+ * - All remaining characters (including all printable
154
+ * ISO 8859-1 and WGL4 characters, Unicode control characters,
155
+ * etc.) have a column width of 1.
157
+ * This implementation assumes that wchar_t characters are encoded
161
+int mk_wcwidth(wchar_t ucs)
163
+ /* sorted list of non-overlapping intervals of non-spacing characters */
164
+ /* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
165
+ static const struct interval combining[] = {
166
+ { 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
167
+ { 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
168
+ { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
169
+ { 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
170
+ { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
171
+ { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
172
+ { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
173
+ { 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
174
+ { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
175
+ { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
176
+ { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
177
+ { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
178
+ { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
179
+ { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
180
+ { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
181
+ { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
182
+ { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
183
+ { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
184
+ { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
185
+ { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
186
+ { 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
187
+ { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
188
+ { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
189
+ { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
190
+ { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
191
+ { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
192
+ { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
193
+ { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
194
+ { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
195
+ { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
196
+ { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
197
+ { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
198
+ { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
199
+ { 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
200
+ { 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
201
+ { 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
202
+ { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
203
+ { 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
204
+ { 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
205
+ { 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
206
+ { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
207
+ { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
208
+ { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
209
+ { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
210
+ { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
211
+ { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
212
+ { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
213
+ { 0xE0100, 0xE01EF }
216
+ /* test for 8-bit control characters */
219
+ if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
222
+ /* binary search in table of non-spacing characters */
223
+ if (bisearch(ucs, combining,
224
+ sizeof(combining) / sizeof(struct interval) - 1))
227
+ /* if we arrive here, ucs is not a combining or C0/C1 control character */
231
+ (ucs <= 0x115f || /* Hangul Jamo init. consonants */
232
+ ucs == 0x2329 || ucs == 0x232a ||
233
+ (ucs >= 0x2e80 && ucs <= 0xa4cf &&
234
+ ucs != 0x303f) || /* CJK ... Yi */
235
+ (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
236
+ (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
237
+ (ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
238
+ (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
239
+ (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
240
+ (ucs >= 0xffe0 && ucs <= 0xffe6) ||
241
+ (ucs >= 0x20000 && ucs <= 0x2fffd) ||
242
+ (ucs >= 0x30000 && ucs <= 0x3fffd)));
246
+int mk_wcswidth(const wchar_t *pwcs, size_t n)
250
+ for (;*pwcs && n-- > 0; pwcs++)
251
+ if ((w = mk_wcwidth(*pwcs)) < 0)
added
removed
doc/wcwidth.patch
