vim-patch:7.4.1604

Problem:    Although emoji characters are ambiguous width, best is to treat
            them as full width.
Solution:   Update the Unicode character tables. Add the 'emoji' options.
            (Yasuhiro Matsumoto)

3848e00e01

runtime/doc/options.txt

@@ -1,4 +1,4 @@
-*options.txt*	For Vim version 7.4.  Last change: 2016 Apr 12
+*options.txt*	For Vim version 7.4.  Last change: 2016 Mar 19
 
 
 		  VIM REFERENCE MANUAL	  by Bram Moolenaar
@@ -899,7 +899,7 @@ A jump table for the options with a short description can be found at |Q_op|.
 	- The backup file will be created in the first directory in the list
 	  where this is possible.  The directory must exist, Vim will not
 	  create it for you.
-	- Empty means that no backup file will be created ( 'patchmode' is
+	- Empty means that no backup file will be created ('patchmode' is
 	  impossible!).  Writing may fail because of this.
 	- A directory "." means to put the backup file in the same directory
 	  as the edited file.
@@ -1456,7 +1456,7 @@ A jump table for the options with a short description can be found at |Q_op|.
 	when CTRL-P or CTRL-N are used.  It is also used for whole-line
 	completion |i_CTRL-X_CTRL-L|.  It indicates the type of completion
 	and the places to scan.  It is a comma separated list of flags:
-	.	scan the current buffer ( 'wrapscan' is ignored)
+	.	scan the current buffer ('wrapscan' is ignored)
 	w	scan buffers from other windows
 	b	scan other loaded buffers that are in the buffer list
 	u	scan the unloaded buffers that are in the buffer list
@@ -2123,6 +2123,15 @@ A jump table for the options with a short description can be found at |Q_op|.
 		hor	horizontally, height of windows is not affected
 		both	width and height of windows is affected
 
+						*'emoji'* *'emo'*
+'emoji' 'emo'	boolean (default: on)
+			global
+			{not in Vi}
+			{only available when compiled with the |+multi_byte|
+			feature}
+	When on all Unicode emoji characters are considered to be full width.
+
+
 					*'encoding'* *'enc'* *E543*
 'encoding' 'enc'	string (default: "utf-8")
 			global
@@ -3082,7 +3091,7 @@ A jump table for the options with a short description can be found at |Q_op|.
 		The same applies to the modeless selection.
 								*'go-P'*
 	  'P'	Like autoselect but using the "+ register instead of the "*
-	  	register.
+		register.
 								*'go-A'*
 	  'A'	Autoselect for the modeless selection.  Like 'a', but only
 		applies to the modeless selection.
@@ -4378,7 +4387,7 @@ A jump table for the options with a short description can be found at |Q_op|.
 	respectively; see |CTRL-A| for more info on these commands.
 	alpha	If included, single alphabetical characters will be
 		incremented or decremented.  This is useful for a list with a
-		letter index a), b), etc.	  	*octal-nrformats*
+		letter index a), b), etc.		*octal-nrformats*
 	octal	If included, numbers that start with a zero will be considered
 		to be octal.  Example: Using CTRL-A on "007" results in "010".
 	hex	If included, numbers starting with "0x" or "0X" will be
@@ -4408,7 +4417,7 @@ A jump table for the options with a short description can be found at |Q_op|.
 	relative to the cursor.  Together with 'number' there are these
 	four combinations (cursor in line 3):
 
-              	'nonu'          'nu'            'nonu'          'nu'
+		'nonu'          'nu'            'nonu'          'nu'
 		'nornu'         'nornu'         'rnu'           'rnu'
 
 	    |apple          |  1 apple      |  2 apple      |  2 apple

runtime/optwin.vim

@@ -1195,6 +1195,8 @@ if has("multi_byte")
   endif
   call append("$", "ambiwidth\twidth of ambiguous width characters")
   call <SID>OptionG("ambw", &ambw)
+  call append("$", "emoji\temoji characters are full width")
+  call <SID>BinOptionG("emo", &emo)
 endif
 
 

scripts/download-unicode-files.sh

@@ -1,11 +1,11 @@
 #!/bin/sh
 
 set -e
-
-files="UnicodeData.txt CaseFolding.txt EastAsianWidth.txt"
+data_files="UnicodeData.txt CaseFolding.txt EastAsianWidth.txt"
+emoji_files="emoji-data.txt"
 
 UNIDIR_DEFAULT=unicode
-DOWNLOAD_URL_BASE_DEFAULT='http://unicode.org/Public/UNIDATA'
+DOWNLOAD_URL_BASE_DEFAULT='http://unicode.org/Public'
 
 if test x$1 = 'x--help' ; then
   echo 'Usage:'
@@ -21,8 +21,16 @@ fi
 UNIDIR=${1:-$UNIDIR_DEFAULT}
 DOWNLOAD_URL_BASE=${2:-$DOWNLOAD_URL_BASE_DEFAULT}
 
-for filename in $files ; do
-  curl -o "$UNIDIR/$filename" "$DOWNLOAD_URL_BASE/$filename"
+for filename in $data_files ; do
+  curl -o "$UNIDIR/$filename" "$DOWNLOAD_URL_BASE/UNIDATA/$filename"
+  (
+    cd "$UNIDIR"
+    git add $filename
+  )
+done
+
+for filename in $emoji_files ; do
+  curl -o "$UNIDIR/$filename" "$DOWNLOAD_URL_BASE/emoji/3.0/$filename"
   (
     cd "$UNIDIR"
     git add $filename

scripts/genunicodetables.lua

@@ -12,10 +12,12 @@
 --    2 then interval applies only to first, third, fifth, … character in range. 
 --    Fourth value is number that should be added to the codepoint to yield 
 --    folded/lower/upper codepoint.
+-- 4. emoji table: sorted list of non-overlapping closed intervals of Emoji
+--    characters
 if arg[1] == '--help' then
   print('Usage:')
   print('  genunicodetables.lua UnicodeData.txt CaseFolding.txt ' ..
-        'EastAsianWidth.txt')
+        'EastAsianWidth.txt emoji-data.txt')
   print('                       unicode_tables.generated.h')
   os.exit(0)
 end
@@ -23,8 +25,9 @@ end
 local unicodedata_fname = arg[1]
 local casefolding_fname = arg[2]
 local eastasianwidth_fname = arg[3]
+local emoji_fname = arg[4]
 
-local utf_tables_fname = arg[4]
+local utf_tables_fname = arg[5]
 
 local split_on_semicolons = function(s)
   local ret = {}
@@ -79,6 +82,10 @@ local parse_width_props = function(eaw_fp)
   return fp_lines_to_lists(eaw_fp, 2, true)
 end
 
+local parse_emoji_props = function(emoji_fp)
+  return fp_lines_to_lists(emoji_fp, 2, true)
+end
+
 local make_range = function(start, end_, step, add)
   if step and add then
     return ('  {0x%x, 0x%x, %d, %d},\n'):format(
@@ -213,6 +220,24 @@ local build_width_table = function(ut_fp, dataprops, widthprops, widths,
   ut_fp:write('};\n')
 end
 
+local build_emoji_table = function(ut_fp, emojiprops)
+  ut_fp:write('static const struct interval emoji[] = {\n')
+  for _, p in ipairs(emojiprops) do
+    if p[2]:match('Emoji%s+#') then
+      local start, end_ = p[1]:find('%.%.')
+      if start then
+        local n = tonumber(p[1]:sub(1, start - 1), 16)
+        local nl = tonumber(p[1]:sub(end_ + 1), 16)
+        ut_fp:write(make_range(n, nl))
+      else
+        local n = tonumber(p[1], 16)
+        ut_fp:write(make_range(n, n))
+      end
+    end
+  end
+  ut_fp:write('};\n')
+end
+
 local ud_fp = io.open(unicodedata_fname, 'r')
 local dataprops = parse_data_to_props(ud_fp)
 ud_fp:close()
@@ -236,4 +261,10 @@ eaw_fp:close()
 build_width_table(ut_fp, dataprops, widthprops, {W=true, F=true}, 'doublewidth')
 build_width_table(ut_fp, dataprops, widthprops, {A=true}, 'ambiguous')
 
+local emoji_fp = io.open(emoji_fname, 'r')
+local emojiprops = parse_emoji_props(emoji_fp)
+emoji_fp:close()
+
+build_emoji_table(ut_fp, emojiprops)
+
 ut_fp:close()

src/nvim/CMakeLists.txt

@@ -39,6 +39,7 @@ set(UNICODE_DIR ${PROJECT_SOURCE_DIR}/unicode)
 set(UNICODEDATA_FILE ${UNICODE_DIR}/UnicodeData.txt)
 set(CASEFOLDING_FILE ${UNICODE_DIR}/CaseFolding.txt)
 set(EASTASIANWIDTH_FILE ${UNICODE_DIR}/EastAsianWidth.txt)
+set(EMOJI_FILE ${UNICODE_DIR}/emoji-data.txt)
 set(GENERATED_UNICODE_TABLES ${GENERATED_DIR}/unicode_tables.generated.h)
 
 include_directories(${GENERATED_DIR})
@@ -195,12 +196,14 @@ add_custom_command(OUTPUT ${GENERATED_UNICODE_TABLES}
                      ${UNICODEDATA_FILE}
                      ${CASEFOLDING_FILE}
                      ${EASTASIANWIDTH_FILE}
+                     ${EMOJI_FILE}
                      ${GENERATED_UNICODE_TABLES}
   DEPENDS
     ${UNICODE_TABLES_GENERATOR}
     ${UNICODEDATA_FILE}
     ${CASEFOLDING_FILE}
     ${EASTASIANWIDTH_FILE}
+    ${EMOJI_FILE}
 )
 
 add_custom_command(OUTPUT ${GENERATED_API_DISPATCH} ${API_METADATA}

src/nvim/mbyte.c

@@ -949,6 +949,9 @@ int utf_char2cells(int c)
     if (intable(doublewidth, ARRAY_SIZE(doublewidth), c))
       return 2;
 #endif
+    if (p_emoji && intable(emoji, ARRAY_SIZE(emoji), c)) {
+      return 2;
+    }
   }
   /* Characters below 0x100 are influenced by 'isprint' option */
   else if (c >= 0x80 && !vim_isprintc(c))

src/nvim/option.c

@@ -2520,7 +2520,7 @@ did_set_string_option (
       errmsg = e_invarg;
   }
   /* 'ambiwidth' */
-  else if (varp == &p_ambw) {
+  else if (varp == &p_ambw || (bool *)varp == &p_emoji) {
     if (check_opt_strings(p_ambw, p_ambw_values, FALSE) != OK)
       errmsg = e_invarg;
     else if (set_chars_option(&p_lcs) != NULL)

src/nvim/option_defs.h

@@ -402,6 +402,7 @@ static char *(p_dy_values[]) = {"lastline", "uhex", NULL};
 #define DY_LASTLINE             0x001
 #define DY_UHEX                 0x002
 EXTERN int p_ed;                /* 'edcompatible' */
+EXTERN bool p_emoji;            // 'emoji'
 EXTERN char_u   *p_ead;         /* 'eadirection' */
 EXTERN bool p_ea;               /* 'equalalways' */
 EXTERN char_u   *p_ep;          /* 'equalprg' */

src/nvim/options.lua

@@ -643,6 +643,14 @@ return {
       varname='p_force_off',
       defaults={if_true={vi=false}}
     },
+    {
+      full_name='emoji', abbreviation='emo',
+      type='bool', scope={'global'},
+      vi_def=true,
+      redraw={'everything'},
+      varname='p_emoji',
+      defaults={if_true={vi=true}}
+    },
     {
       full_name='encoding', abbreviation='enc',
       type='string', scope={'global'},

src/nvim/version.c

@@ -839,7 +839,7 @@ static int included_patches[] = {
   // 1607,
   // 1606,
   // 1605,
-  // 1604,
+  1604,
   1603,
   // 1602 NA
   // 1601 NA