Set of changes to improve Unicode support with respect to combining characters.

Should address https://github.com/fish-shell/fish-shell/issues/155

common.cpp

@@ -511,18 +511,7 @@ int wcsvarchr( wchar_t chr )
 */
 int my_wcswidth( const wchar_t *c )
 {
-	int res=0;
+	return fish_wcswidth(c, wcslen(c));
-	while( *c )
-	{
-		int w = wcwidth( *c++ );
-		if( w < 0 )
-			w = 1;
-		if( w > 2 )
-			w=1;
-		
-		res += w;		
-	}
-	return res;
 }
 
 wchar_t *quote_end( const wchar_t *pos )
@@ -822,13 +811,13 @@ void write_screen( const wcstring &msg, wcstring &buff )
 				  Check is token is wider than one line.
 				  If so we mark it as an overflow and break the token.
 				*/
-				if((tok_width + wcwidth(*pos)) > (screen_width-1))
+				if((tok_width + fish_wcwidth(*pos)) > (screen_width-1))
 				{
 					overflow = 1;
 					break;				
 				}
 			
-				tok_width += wcwidth( *pos );
+				tok_width += fish_wcwidth( *pos );
 				pos++;
 			}
 

fallback.cpp

@@ -1192,3 +1192,258 @@ double nan(char *tagp)
 }
 #endif
 
+/* Big hack to use our versions of wcswidth where we know them to be broken, like on OS X */
+#ifndef HAVE_BROKEN_WCWIDTH
+ #if __APPLE__
+  #define HAVE_BROKEN_WCWIDTH 1
+ #else
+  #define HAVE_BROKEN_WCWIDTH 0
+ #endif
+#endif
+
+#if ! HAVE_BROKEN_WCWIDTH
+
+int fish_wcwidth(wchar_t wc)
+{
+    return wcwidth(wc);
+}
+
+int fish_wcswidth(const wchar_t *str, size_t n)
+{
+    return wcswidth(str, n);
+}
+
+#else
+
+static int mk_wcwidth(wchar_t wc);
+static int mk_wcswidth(const wchar_t *pwcs, size_t n);
+
+int fish_wcwidth(wchar_t wc)
+{
+    return mk_wcwidth(wc);
+}
+
+int fish_wcswidth(const wchar_t *str, size_t n)
+{
+    return mk_wcswidth(str, n);
+}
+
+/*
+ * 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 <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.
+ */
+
+static 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) ||
+      (ucs >= 0x20000 && ucs <= 0x2fffd) ||
+      (ucs >= 0x30000 && ucs <= 0x3fffd)));
+}
+
+static int mk_wcswidth(const wchar_t *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 // HAVE_BROKEN_WCWIDTH

fallback.h

@@ -12,6 +12,10 @@
 #include <sys/types.h>
 #include <signal.h>
 
+/** fish's internal versions of wcwidth and wcswidth, which can use an internal implementation if the system one is busted. */
+int fish_wcwidth(wchar_t wc);
+int fish_wcswidth(const wchar_t *str, size_t n);
+
 #ifndef WCHAR_MAX
 /**
    This _should_ be defined by wchar.h, but e.g. OpenBSD doesn't.

output.cpp

@@ -507,8 +507,8 @@ void writestr_ellipsis( const wchar_t *str, int max_width )
     
 	while( *str != 0 )
 	{
-		int w = wcwidth( *str );
+		int w = fish_wcwidth( *str );
-		if( written+w+wcwidth( ellipsis_char )>max_width )
+		if( written+w+fish_wcwidth( ellipsis_char )>max_width )
 		{
 			break;
 		}
@@ -516,7 +516,7 @@ void writestr_ellipsis( const wchar_t *str, int max_width )
 		writech( *(str++) );
 	}
     
-	written += wcwidth( ellipsis_char );
+	written += fish_wcwidth( ellipsis_char );
 	writech( ellipsis_char );
     
 	while( written < max_width )
@@ -541,13 +541,13 @@ int write_escaped_str( const wchar_t *str, int max_len )
     
 	if( max_len && (max_len < len))
 	{
-		for( i=0; (written+wcwidth(out[i]))<=(max_len-1); i++ )
+		for( i=0; (written+fish_wcwidth(out[i]))<=(max_len-1); i++ )
 		{
 			writech( out[i] );
-			written += wcwidth( out[i] );
+			written += fish_wcwidth( out[i] );
 		}
 		writech( ellipsis_char );
-		written += wcwidth( ellipsis_char );
+		written += fish_wcwidth( ellipsis_char );
 		
 		for( i=written; i<max_len; i++ )
 		{

parser.cpp

@@ -1080,7 +1080,7 @@ static int printed_width( const wchar_t *str, int len )
 		}
 		else
 		{
-			res += wcwidth( str[i] );
+			res += fish_wcwidth( str[i] );
 		}
 	}
 	return res;

reader.cpp

@@ -722,8 +722,13 @@ static void remove_backward()
 	if( data->buff_pos <= 0 )
 		return;
     
-    data->command_line.erase(data->buff_pos-1, 1);    
+    /* Fake composed character sequences by continuning to delete until we delete a character of width at least 1. */
-	data->buff_pos--;
+    int width;
+    do {
+        data->buff_pos -= 1;
+        width = fish_wcwidth(data->command_line.at(data->buff_pos));
+        data->command_line.erase(data->buff_pos, 1);        
+    } while (width == 0 && data->buff_pos > 0);
     data->command_line_changed();
     data->suppress_autosuggestion = true;
 

screen.cpp

@@ -300,7 +300,7 @@ static int calc_prompt_width( const wchar_t *prompt )
 			/*
 			  Ordinary decent character. Just add width.
 			*/
-			res += wcwidth( prompt[j] );
+			res += fish_wcwidth( prompt[j] );
 		}
 	}
 	return res;
@@ -425,7 +425,7 @@ static void s_desired_append_char( screen_t *s,
 		case L'\n':
 		{
 			int i;
-            s->desired.add_line();
+            s->desired.create_line(s->desired.line_count());
 			s->desired.cursor[1]++;
 			s->desired.cursor[0]=0;
 			for( i=0; i < prompt_width+indent*INDENT_STEP; i++ )
@@ -438,7 +438,7 @@ static void s_desired_append_char( screen_t *s,
 		case L'\r':
 		{
             line_t &current = s->desired.line(line_no);
-            current.resize(0);
+            current.clear();
             s->desired.cursor[0] = 0;
 			break;			
 		}		
@@ -446,8 +446,8 @@ static void s_desired_append_char( screen_t *s,
 		default:
 		{
 			int screen_width = common_get_width();
-			int cw = wcwidth(b);
+			int cw = fish_wcwidth(b);
-			int ew = wcwidth( ellipsis_char );
+			int ew = fish_wcwidth( ellipsis_char );
 			int i;
 			
             s->desired.create_line(line_no);
@@ -458,9 +458,7 @@ static void s_desired_append_char( screen_t *s,
 			*/
 			if( s->desired.cursor[0] + cw + ew > screen_width )
 			{
-                line_entry_t &entry = s->desired.line(line_no).create_entry(s->desired.cursor[0]);
+                s->desired.line(line_no).append(ellipsis_char, HIGHLIGHT_COMMENT);
-                entry.text = ellipsis_char;
-                entry.color = HIGHLIGHT_COMMENT;
                 
                 line_no = s->desired.line_count();
                 s->desired.add_line();
@@ -474,8 +472,7 @@ static void s_desired_append_char( screen_t *s,
 			}
 			
             line_t &line = s->desired.line(line_no);
-            line.create_entry(s->desired.cursor[0]).text = b;
+            line.append(b, c);
-            line.create_entry(s->desired.cursor[0]).color = c;
 			s->desired.cursor[0]+= cw;
 			break;
 		}
@@ -553,7 +550,8 @@ static void s_move( screen_t *s, data_buffer_t *b, int new_x, int new_y )
 		x_steps = 0;
 	}
 		
-	if( x_steps < 0 ){
+	if( x_steps < 0 )
+    {
 		str = cursor_left;
 	}
 	else
@@ -590,10 +588,23 @@ static void s_set_color( screen_t *s, data_buffer_t *b, int c )
 static void s_write_char( screen_t *s, data_buffer_t *b, wchar_t c )
 {
 	scoped_buffer_t scoped_buffer(b);
-	s->actual.cursor[0]+=wcwidth( c );	
+	s->actual.cursor[0]+=fish_wcwidth( c );	
 	writech( c );
 }
 
+/**
+   Convert a wide string to a multibyte string and append it to the
+   buffer. Returns the width.
+*/
+static int s_write_string( screen_t *s, data_buffer_t *b, const wcstring &str )
+{
+	scoped_buffer_t scoped_buffer(b);
+    int width = fish_wcswidth(str.c_str(), str.size());
+	writestr(str.c_str());
+    s->actual.cursor[0] += width;
+    return width;
+}
+
 /**
    Send the specified string through tputs and append the output to
    the specified buffer.
@@ -614,14 +625,36 @@ static void s_write_str( data_buffer_t *b, const wchar_t *s )
 	writestr( s );
 }
 
+/** Returns the length of the "shared prefix" of the two lines, which is the run of matching text and colors.
+    If the prefix ends on a combining character, do not include the previous character in the prefix.
+*/
+static size_t line_shared_prefix(const line_t &a, const line_t &b)
+{
+    size_t idx, max = std::min(a.size(), b.size());
+    for (idx=0; idx < max; idx++)
+    {            
+        wchar_t ac = a.char_at(idx), bc = b.char_at(idx);
+        if (fish_wcwidth(ac) < 1 || fish_wcwidth(bc) < 1)
+        {
+            /* Possible combining mark, return one index prior */
+            if (idx > 0) idx--;
+            break;
+        }
+        
+        /* We're done if the text or colors are different */
+        if (ac != bc || a.color_at(idx) != b.color_at(idx))
+            break;
+    }
+    return idx;
+}
+
 /**
    Update the screen to match the desired output.
 */
 static void s_update( screen_t *scr, const wchar_t *prompt )
 {
-	size_t i, j;
+	size_t i;
 	int prompt_width = calc_prompt_width( prompt );
-	int current_width=0;
 	int screen_width = common_get_width();
 	int need_clear = scr->need_clear;
 	data_buffer_t output;
@@ -646,74 +679,75 @@ static void s_update( screen_t *scr, const wchar_t *prompt )
 	
     for (i=0; i < scr->desired.line_count(); i++)
 	{
-		line_t &o_line = scr->desired.line(i);
+		const line_t &o_line = scr->desired.line(i);
 		line_t &s_line = scr->actual.create_line(i);
-		int start_pos = (i==0?prompt_width:0);
+		int start_pos = (i==0 ? prompt_width : 0);
-		current_width = start_pos;
+        int current_width = 0;
         
 		if( need_clear )
 		{
 			s_move( scr, &output, start_pos, i );
 			s_write_mbs( &output, clr_eol);
-            s_line.resize(0);
+            s_line.clear();
 		}
         
-        for( j=start_pos; j<o_line.entry_count(); j++) 
+        /* Note that skip_remaining is a width, not a character count */
-		{
+        int skip_remaining = start_pos;
-            line_entry_t &entry = o_line.entry(j);
-			wchar_t o = entry.text;
-			int o_c = entry.color;
-			if( !o )
-				continue;
         
-			if( s_line.entry_count() == j )
+        /* Compute how much we should skip. At a minimum we skip over the prompt. But also skip over the shared prefix of what we want to output now, and what we output before, to avoid repeatedly outputting it. */
-			{
+        size_t shared_prefix = line_shared_prefix(o_line, s_line);
-				s_move( scr, &output, current_width, i );
+        if (shared_prefix > 0)
-				s_set_color( scr, &output, o_c );
+        {
-				s_write_char( scr, &output, o );
+            int prefix_width = fish_wcswidth(&o_line.text.at(0), shared_prefix);
-                s_line.create_entry(j).text = o;
+            if (prefix_width > skip_remaining)
-                s_line.create_entry(j).color = o_c;
+                skip_remaining = prefix_width;
-			}
+        }
-			else
-			{
-                line_entry_t &entry = s_line.create_entry(j);
-                wchar_t s = entry.text;
-                int s_c = entry.color;
         
-				if( o != s || o_c != s_c )
+        /* Skip over skip_remaining width worth of characters */
-				{
+        size_t j = 0;
-					s_move( scr, &output, current_width, i );
+        for ( ; j < o_line.size(); j++)
-					s_set_color( scr, &output, o_c );
+        {
-					s_write_char( scr, &output, o );
+            int width = fish_wcwidth(o_line.char_at(j));
+            skip_remaining -= width;
+            if (skip_remaining <= 0)
+                break;
+            current_width += width;
+        }
         
-                    s_line.create_entry(current_width).text = o;
+        /* Skip over zero-width characters (e.g. combining marks at the end of the prompt) */
-                    s_line.create_entry(current_width).color = o_c;
+        for ( ; j < o_line.size(); j++)
-					for( int k=1; k<wcwidth(o); k++ )
+        {
-                        s_line.create_entry(current_width+k).text = L'\0';
+            int width = fish_wcwidth(o_line.char_at(j));
+            if (width > 0)
+                break;
+        }
         
-				}
+        /* Now actually output stuff */
-			}
+        for ( ; j < o_line.size(); j++)
-			current_width += wcwidth( o );
+        {
-		}
+            s_move( scr, &output, current_width, i );
+            s_set_color( scr, &output, o_line.color_at(j) );
+            s_write_char( scr, &output, o_line.char_at(j) );
+            current_width += fish_wcwidth(o_line.char_at(j));
+        }
         
-        if ( s_line.entry_count() > o_line.entry_count() )
+        /* If we wrote more on this line last time, clear it */
+        int prev_length = (s_line.text.empty() ? 0 : fish_wcswidth(&s_line.text.at(0), s_line.text.size()));
+        if (prev_length > current_width )
 		{
 			s_move( scr, &output, current_width, i );
 			s_write_mbs( &output, clr_eol);
-            s_line.resize(o_line.entry_count());
 		}
-		
 	}
+    
+    /* Clear remaining lines */
     for( i=scr->desired.line_count(); i < scr->actual.line_count(); i++ )
 	{
-        line_t &s_line = scr->actual.create_line(i);
 		s_move( scr, &output, 0, i );
 		s_write_mbs( &output, clr_eol);
-        s_line.resize(0);
 	}
 	
 	s_move( scr, &output, scr->desired.cursor[0], scr->desired.cursor[1] );
-	
 	s_set_color( scr, &output, 0xffffffff);
 
 	if( ! output.empty() )
@@ -721,6 +755,8 @@ static void s_update( screen_t *scr, const wchar_t *prompt )
 		write_loop( 1, &output.at(0), output.size() );
 	}
 	
+    /* We have now synced our actual screen against our desired screen. Note that this is a big assignment! */
+    scr->actual = scr->desired;
 }
 
 /**
@@ -815,7 +851,7 @@ void s_write( screen_t *s,
 		}
 		else
 		{
-            int width = wcwidth(commandline[i]);
+            int width = fish_wcwidth(commandline[i]);
 			current_line_width += width;
             if (i < explicit_len)
                 explicit_portion_width += width;
@@ -884,7 +920,7 @@ void s_write( screen_t *s,
 			   cursor won't be on the ellipsis which looks
 			   unintuitive.
 			*/
-			cursor_arr[0] = s->desired.cursor[0] - wcwidth(commandline[i]);
+			cursor_arr[0] = s->desired.cursor[0] - fish_wcwidth(commandline[i]);
 			cursor_arr[1] = s->desired.cursor[1];
 		}
 		

screen.h

@@ -14,38 +14,41 @@
 
 #include <vector>
 
-struct line_entry_t
-{
-    wchar_t text;
-    int color;
-};
-
 /**
    A class representing a single line of a screen.
 */
-class line_t
+struct line_t
 {
-    public:
+    std::vector<wchar_t> text;
-    std::vector<struct line_entry_t> entries;
+    std::vector<int> colors;
     
-    void resize(size_t size) {
+    void clear(void)
-        entries.resize(size);
+    {
+        text.clear();
+        colors.clear();
     }
     
-    line_entry_t &entry(size_t idx) {
+    void append(wchar_t txt, int color)
-        return entries.at(idx);
+    {
+        text.push_back(txt);
+        colors.push_back(color);
     }
         
-    line_entry_t &create_entry(size_t idx) {
+    size_t size(void) const
-        if (idx >= entries.size()) {
+    {
-            entries.resize(idx + 1);
+        return text.size();
-        }
-        return entries.at(idx);
     }
     
-    size_t entry_count(void) {
+    wchar_t char_at(size_t idx) const
-        return entries.size();
+    {
+        return text.at(idx);
     }
+    
+    int color_at(size_t idx) const
+    {
+        return colors.at(idx);
+    }
+    
 };
 
 /**