Replace utf8_width with Markus Kuhn's wcwidth.

git-svn-id: http://svn.irssi.org/repos/irssi/trunk@4518 dbcabf3a-b0e7-0310-adc4-f8d773084564

src/fe-common/core/Makefile.am

@@ -26,6 +26,7 @@ libfe_common_core_a_SOURCES = \
 	fe-server.c \
 	fe-settings.c \
 	utf8.c \
+	wcwidth.c \
 	formats.c \
 	hilight-text.c \
 	keyboard.c \

src/fe-common/core/formats.c

@@ -306,7 +306,7 @@ static int advance (char const **str, gboolean utf8)
 		c = g_utf8_get_char(*str);
 		*str = g_utf8_next_char(*str);
 
-		return utf8_width(c);
+		return mk_wcwidth(c);
 	} else {
 		*str += 1;
 

src/fe-common/core/utf8.c

@@ -7,10 +7,6 @@
  * Copyright (C) 1999 Tom Tromey
  * Copyright (C) 2000 Red Hat, Inc.
  *
- * UTF-8 width tables based on locale data from GNU libc by
- *
- * Copyright (C) 1991-2002 Free Software Foundation, Inc.
- *
  * This library is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Lesser General Public
  * License as published by the Free Software Foundation; either
@@ -198,73 +194,3 @@ void utf16_to_utf8_with_pos(const unichar *str, int spos, char *out, int *opos)
 	}
 	*out = '\0';
 }
-
-static const unichar wcc[] = {
-	0x0, 0x300, 0x34F, 0x360, 0x363, 0x483, 0x487, 0x488, 0x48A, 0x591,
-	0x5A2, 0x5A3, 0x5BA, 0x5BB, 0x5BE, 0x5BF, 0x5C0, 0x5C1, 0x5C3, 0x5C4,
-	0x5C5, 0x64B, 0x656, 0x670, 0x671, 0x6D6, 0x6E5, 0x6E7, 0x6E9, 0x6EA,
-	0x6EE, 0x70F, 0x710, 0x711, 0x712, 0x730, 0x74B, 0x7A6, 0x7B1, 0x901,
-	0x903, 0x93C, 0x93D, 0x941, 0x949, 0x94D, 0x94E, 0x951, 0x955, 0x962,
-	0x964, 0x981, 0x982, 0x9BC, 0x9BD, 0x9C1, 0x9C5, 0x9CD, 0x9CE, 0x9E2,
-	0x9E4, 0xA02, 0xA03, 0xA3C, 0xA3D, 0xA41, 0xA43, 0xA47, 0xA49, 0xA4B,
-	0xA4E, 0xA70, 0xA72, 0xA81, 0xA83, 0xABC, 0xABD, 0xAC1, 0xAC6, 0xAC7,
-	0xAC9, 0xACD, 0xACE, 0xB01, 0xB02, 0xB3C, 0xB3D, 0xB3F, 0xB40, 0xB41,
-	0xB44, 0xB4D, 0xB4E, 0xB56, 0xB57, 0xB82, 0xB83, 0xBC0, 0xBC1, 0xBCD,
-	0xBCE, 0xC3E, 0xC41, 0xC46, 0xC49, 0xC4A, 0xC4E, 0xC55, 0xC57, 0xCBF,
-	0xCC0, 0xCC6, 0xCC7, 0xCCC, 0xCCE, 0xD41, 0xD44, 0xD4D, 0xD4E, 0xDCA,
-	0xDCB, 0xDD2, 0xDD5, 0xDD6, 0xDD7, 0xE31, 0xE32, 0xE34, 0xE3B, 0xE47,
-	0xE4F, 0xEB1, 0xEB2, 0xEB4, 0xEBA, 0xEBB, 0xEBD, 0xEC8, 0xECE, 0xF18,
-	0xF1A, 0xF35, 0xF36, 0xF37, 0xF38, 0xF39, 0xF3A, 0xF71, 0xF7F, 0xF80,
-	0xF85, 0xF86, 0xF88, 0xF90, 0xF98, 0xF99, 0xFBD, 0xFC6, 0xFC7, 0x102D,
-	0x1031, 0x1032, 0x1033, 0x1036, 0x1038, 0x1039, 0x103A, 0x1058, 0x105A,
-	0x1100, 0x1160, 0x17B7, 0x17BE, 0x17C6, 0x17C7, 0x17C9, 0x17D4, 0x180B,
-	0x180F, 0x18A9, 0x18AA, 0x200B, 0x2010, 0x202A, 0x202F, 0x206A, 0x2070,
-	0x20D0, 0x20E4, 0x2E80, 0x3008, 0x300C, 0x3014, 0x3016, 0x3018, 0x301C,
-	0x302A, 0x3030, 0x303F, 0x3041, 0x3095, 0x3099, 0x309B, 0xA4C7, 0xAC00,
-	0xD7A4, 0xF8F0, 0xF900, 0xFA2E, 0xFB1E, 0xFB1F, 0xFE20, 0xFE24, 0xFE30,
-	0xFE6C, 0xFEFF, 0xFF00, 0xFF01, 0xFF5F, 0xFFE0, 0xFFE7, 0xFFF9, 0xFFFC,
-#if 1
-	0x1D167, 0x1D16A, 0x1D173, 0x1D183, 0x1D185, 0x1D18C, 0x1D1AA, 0x1D1AE,
-	0x20000, 0x2A6D7, 0x2F800, 0x2FA1E, 0xE0001, 0xE0002, 0xE0020, 0xE0080
-#endif
-};
-
-static const int wccnum = sizeof(wcc) / sizeof(wcc[0]) - 1;
-
-static const char wws[] = {
-	1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
-	1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
-	1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
-	1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
-	1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
-	1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
-	1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
-	1, 2, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 2, 1, 2,
-	1, 2, 1, 2, 0, 2, 1, 2, 1, 0, 2, 1, 2, 1, 0, 2, 1, 0, 1, 0, 1, 2, 1, 0,
-	1, 2, 1, 2, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 2, 1, 2, 1, 0, 1, 0, 1, -1
-};
-
-int utf8_width(unichar c)
-{
-	int p, q, r;
-	unichar d;
-
-	if (c < wcc[1])
-		return 1;
-
-	p = 0;
-	q = wccnum;
-
-	while (p < q - 1) {
-		r = (p + q)/2;
-		d = wcc[r];
-		if (d < c)
-			p = r;
-		else if (d > c)
-			q = r;
-		else
-			return wws[r];
-	}
-
-	return wws[p];
-}

src/fe-common/core/utf8.h

@@ -30,6 +30,6 @@ void utf16_to_utf8_with_pos(const unichar *str, int spos, char *out, int *opos);
 #define is_big5(hi,lo) (is_big5_hi(hi) && is_big5_lo(lo))
 
 /* Returns width for character (0-2). */
-int utf8_width(unichar c);
+int mk_wcwidth(unichar c);
 
 #endif

src/fe-common/core/wcwidth.c

@@ -0,0 +1,220 @@
+/*
+ * 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 -- 2007-05-25 (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 "module.h"
+
+struct interval {
+  int first;
+  int last;
+};
+
+/* auxiliary function for binary search in interval table */
+static int bisearch(unichar 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(unichar 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)));
+}
+
+
+#if 0
+int mk_wcswidth(const unichar *pwcs, size_t n)
+{
+  int w, width = 0;
+
+  for (;*pwcs && n-- > 0; pwcs++)
+    if ((w = mk_wcwidth(*pwcs)) < 0)
+      return -1;
+    else
+      width += w;
+
+  return width;
+}
+#endif

src/fe-text/gui-entry.c

@@ -141,7 +141,7 @@ static int pos2scrpos(GUI_ENTRY_REC *entry, int pos)
 		if (term_type == TERM_TYPE_BIG5)
 			xpos += big5_width(*p);
 		else if (entry->utf8)
-			xpos += utf8_width(*p);
+			xpos += mk_wcwidth(*p);
 		else
 			xpos++;
 	}
@@ -158,7 +158,7 @@ static int scrpos2pos(GUI_ENTRY_REC *entry, int pos)
 		if (term_type == TERM_TYPE_BIG5)
 			width = big5_width(*p);
 		else if (entry->utf8)
-			width = utf8_width(*p);
+			width = mk_wcwidth(*p);
 		else
 			width = 1;
 
@@ -223,7 +223,7 @@ static void gui_entry_draw_from(GUI_ENTRY_REC *entry, int pos)
 		else if (term_type == TERM_TYPE_BIG5)
 			xpos += big5_width(*p);
 		else if (entry->utf8)
-			xpos += utf8_width(*p);
+			xpos += mk_wcwidth(*p);
 		else
 			xpos++;
 
@@ -513,7 +513,7 @@ static size_t cell_width(unichar *buf, int len)
 {
 	unichar *str = buf;
 
-	while (len-- && utf8_width(*str--) == 0);
+	while (len-- && mk_wcwidth(*str--) == 0);
 	return buf - str;
 }
 

src/fe-text/term-terminfo.c

@@ -425,7 +425,7 @@ void term_add_unichar(TERM_WINDOW *window, unichar chr)
 
 	switch (term_type) {
 	case TERM_TYPE_UTF8:
-	  	term_printed_text(utf8_width(chr));
+	  	term_printed_text(mk_wcwidth(chr));
                 term_addch_utf8(window, chr);
 		break;
 	case TERM_TYPE_BIG5:

src/fe-text/textbuffer-view.c

@@ -218,7 +218,7 @@ view_update_line_cache(TEXT_BUFFER_VIEW_REC *view, LINE_REC *line)
 			if (get_utf8_char(&next_ptr, char_len, &chr) < 0)
 				char_len = 1;
 			else
-				char_len = utf8_width(chr);
+				char_len = mk_wcwidth(chr);
 			next_ptr++;
 		}
 
@@ -439,7 +439,7 @@ static int view_line_draw(TEXT_BUFFER_VIEW_REC *view, LINE_REC *line,
 			if (get_utf8_char(&end, 6, &chr)<0)
 				char_width = 1;
 			else
-				char_width = utf8_width(chr);
+				char_width = mk_wcwidth(chr);
 		} else {
 			if (term_type == TERM_TYPE_BIG5 &&
 			    is_big5(end[0], end[1]))