updated for version 7.2.330v7.2.330

Problem:    Tables for Unicode case operators are outdated.
Solution:   Add a Vim script for generating the tables.  Include tables for
            Unicode 5.2.

4 files changed, 1119 insertions, 204 deletions

diff --git a/runtime/tools/README.txt b/runtime/tools/README.txt
index f5274df22d..fa176c776d 100644
--- a/runtime/tools/README.txt
+++ b/runtime/tools/README.txt
@@ -32,4 +32,6 @@ vim_vs_net.cmd: MS-Windows command file to use Vim with MS Visual Studio 7 and
 xcmdsrv_client.c:  Example for a client program that communicates with a Vim
 		   server through the X-Windows interface.
 
+unicode.vim	Vim script to generate tables for src/mbyte.c.
+
 [xxd (and tee for OS/2) can be found in the src directory]
diff --git a/runtime/tools/unicode.vim b/runtime/tools/unicode.vim
new file mode 100644
index 0000000000..f33df4206d
--- /dev/null
+++ b/runtime/tools/unicode.vim
@@ -0,0 +1,280 @@
+" Script to extract tables from Unicode .txt files, to be used in src/mbyte.c.
+" The format of the UnicodeData.txt file is explained here:
+" http://www.unicode.org/Public/5.1.0/ucd/UCD.html
+" For the other files see the header.
+"
+" Usage: Vim -S <this-file>
+"
+" Author: Bram Moolenaar
+" Last Update: 2010 Jan 12
+
+" Parse lines of UnicodeData.txt.  Creates a list of lists in s:dataprops.
+func! ParseDataToProps()
+  let s:dataprops = []
+  let lnum = 1
+  while lnum <= line('$')
+    let l = split(getline(lnum), '\s*;\s*', 1)
+    if len(l) != 15
+      echoerr 'Found ' . len(l) . ' items in line ' . lnum . ', expected 15'
+      return
+    endif
+    call add(s:dataprops, l)
+    let lnum += 1
+  endwhile
+endfunc
+
+" Parse lines of CaseFolding.txt.  Creates a list of lists in s:foldprops.
+func! ParseFoldProps()
+  let s:foldprops = []
+  let lnum = 1
+  while lnum <= line('$')
+    let line = getline(lnum)
+    if line !~ '^#' && line !~ '^\s*$'
+      let l = split(line, '\s*;\s*', 1)
+      if len(l) != 4
+	echoerr 'Found ' . len(l) . ' items in line ' . lnum . ', expected 4'
+	return
+      endif
+      call add(s:foldprops, l)
+    endif
+    let lnum += 1
+  endwhile
+endfunc
+
+" Parse lines of EastAsianWidth.txt.  Creates a list of lists in s:widthprops.
+func! ParseWidthProps()
+  let s:widthprops = []
+  let lnum = 1
+  while lnum <= line('$')
+    let line = getline(lnum)
+    if line !~ '^#' && line !~ '^\s*$'
+      let l = split(line, '\s*;\s*', 1)
+      if len(l) != 2
+	echoerr 'Found ' . len(l) . ' items in line ' . lnum . ', expected 2'
+	return
+      endif
+      call add(s:widthprops, l)
+    endif
+    let lnum += 1
+  endwhile
+endfunc
+
+" Build the toLower or toUpper table in a new buffer.
+" Uses s:dataprops.
+func! BuildCaseTable(name, index)
+  let start = -1
+  let end = -1
+  let step = 0
+  let add = -1
+  let ranges = []
+  for p in s:dataprops
+    if p[a:index] != ''
+      let n = ('0x' . p[0]) + 0
+      let nl = ('0x' . p[a:index]) + 0
+      if start >= 0 && add == nl - n && (step == 0 || n - end == step)
+	" continue with same range.
+	let step = n - end
+	let end = n
+      else
+	if start >= 0
+	  " produce previous range
+	  call Range(ranges, start, end, step, add)
+	endif
+	let start = n
+	let end = n
+	let step = 0
+	let add = nl - n
+      endif
+    endif
+  endfor
+  if start >= 0
+    call Range(ranges, start, end, step, add)
+  endif
+
+  " New buffer to put the result in.
+  new
+  exe "file to" . a:name
+  call setline(1, "static convertStruct to" . a:name . "[] =")
+  call setline(2, "{")
+  call append('$', ranges)
+  call setline('$', getline('$')[:-2])  " remove last comma
+  call setline(line('$') + 1, "};")
+  wincmd p
+endfunc
+
+" Build the foldCase table in a new buffer.
+" Uses s:foldprops.
+func! BuildFoldTable()
+  let start = -1
+  let end = -1
+  let step = 0
+  let add = -1
+  let ranges = []
+  for p in s:foldprops
+    if p[1] == 'C' || p[1] == 'S'
+      let n = ('0x' . p[0]) + 0
+      let nl = ('0x' . p[2]) + 0
+      if start >= 0 && add == nl - n && (step == 0 || n - end == step)
+	" continue with same range.
+	let step = n - end
+	let end = n
+      else
+	if start >= 0
+	  " produce previous range
+	  call Range(ranges, start, end, step, add)
+	endif
+	let start = n
+	let end = n
+	let step = 0
+	let add = nl - n
+      endif
+    endif
+  endfor
+  if start >= 0
+    call Range(ranges, start, end, step, add)
+  endif
+
+  " New buffer to put the result in.
+  new
+  file foldCase
+  call setline(1, "static convertStruct foldCase[] =")
+  call setline(2, "{")
+  call append('$', ranges)
+  call setline('$', getline('$')[:-2])  " remove last comma
+  call setline(line('$') + 1, "};")
+  wincmd p
+endfunc
+
+func! Range(ranges, start, end, step, add)
+  let s = printf("\t{0x%x,0x%x,%d,%d},", a:start, a:end, a:step == 0 ? -1 : a:step, a:add)
+  call add(a:ranges, s)
+endfunc
+
+" Build the combining table.
+" Uses s:dataprops.
+func! BuildCombiningTable()
+  let start = -1
+  let end = -1
+  let ranges = []
+  for p in s:dataprops
+    if p[2] == 'Mn' || p[2] == 'Mc' || p[2] == 'Me'
+      let n = ('0x' . p[0]) + 0
+      if start >= 0 && end + 1 == n
+	" continue with same range.
+	let end = n
+      else
+	if start >= 0
+	  " produce previous range
+	  call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
+	endif
+	let start = n
+	let end = n
+      endif
+    endif
+  endfor
+  if start >= 0
+    call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
+  endif
+
+  " New buffer to put the result in.
+  new
+  file combining
+  call setline(1, "    static struct interval combining[] =")
+  call setline(2, "    {")
+  call append('$', ranges)
+  call setline('$', getline('$')[:-2])  " remove last comma
+  call setline(line('$') + 1, "    };")
+  wincmd p
+endfunc
+
+" Build the ambiguous table in a new buffer.
+" Uses s:widthprops and s:dataprops.
+func! BuildAmbiguousTable()
+  let start = -1
+  let end = -1
+  let ranges = []
+  let dataidx = 0
+  for p in s:widthprops
+    if p[1][0] == 'A'
+      let n = ('0x' . p[0]) + 0
+      " Find this char in the data table.
+      while 1
+	let dn = ('0x' . s:dataprops[dataidx][0]) + 0
+	if dn >= n
+	  break
+	endif
+	let dataidx += 1
+      endwhile
+      if dn != n
+	echoerr "Cannot find character " . n . " in data table"
+      endif
+      " Only use the char when it's not a composing char.
+      let dp = s:dataprops[dataidx]
+      if dp[2] != 'Mn' && dp[2] != 'Mc' && dp[2] != 'Me'
+	if start >= 0 && end + 1 == n
+	  " continue with same range.
+	  let end = n
+	else
+	  if start >= 0
+	    " produce previous range
+	    call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
+	  endif
+	  let start = n
+	  if p[0] =~ '\.\.'
+	    let end = ('0x' . substitute(p[0], '.*\.\.', '', '')) + 0
+	  else
+	    let end = n
+	  endif
+	endif
+      endif
+    endif
+  endfor
+  if start >= 0
+    call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
+  endif
+
+  " New buffer to put the result in.
+  new
+  file ambiguous
+  call setline(1, "    static struct interval ambiguous[] =")
+  call setline(2, "    {")
+  call append('$', ranges)
+  call setline('$', getline('$')[:-2])  " remove last comma
+  call setline(line('$') + 1, "    };")
+  wincmd p
+endfunc
+
+
+
+" Edit the Unicode text file.  Requires the netrw plugin.
+edit http://unicode.org/Public/UNIDATA/UnicodeData.txt
+
+" Parse each line, create a list of lists.
+call ParseDataToProps()
+
+" Build the toLower table.
+call BuildCaseTable("Lower", 13)
+
+" Build the toUpper table.
+call BuildCaseTable("Upper", 12)
+
+" Build the ranges of composing chars.
+call BuildCombiningTable()
+
+" Edit the case folding text file.  Requires the netrw plugin.
+edit http://www.unicode.org/Public/UNIDATA/CaseFolding.txt
+
+" Parse each line, create a list of lists.
+call ParseFoldProps()
+
+" Build the foldCase table.
+call BuildFoldTable()
+
+" Edit the width text file.  Requires the netrw plugin.
+edit http://www.unicode.org/Public/UNIDATA/EastAsianWidth.txt
+
+" Parse each line, create a list of lists.
+call ParseWidthProps()
+
+" Build the ambiguous table.
+call BuildAmbiguousTable()
diff --git a/src/mbyte.c b/src/mbyte.c
index 530a8e90d0..b5ea292046 100644
--- a/src/mbyte.c
+++ b/src/mbyte.c
@@ -26,7 +26,7 @@
  *		    Recognizing bytes is easy: 0xxx.xxxx is a single-byte
  *		    char, 10xx.xxxx is a trailing byte, 11xx.xxxx is a leading
  *		    byte of a multi-byte character.
- *		    To make things complicated, up to two composing characters
+ *		    To make things complicated, up to six composing characters
  *		    are allowed.  These are drawn on top of the first char.
  *		    For most editing the sequence of bytes with composing
  *		    characters included is considered to be one character.
@@ -1153,8 +1153,8 @@ dbcs_ptr2len_len(p, size)
 
 struct interval
 {
-    unsigned short first;
-    unsigned short last;
+    long first;
+    long last;
 };
 static int intable __ARGS((struct interval *table, size_t size, int c));
 
@@ -1200,62 +1200,191 @@ intable(table, size, c)
 utf_char2cells(c)
     int		c;
 {
-    /* sorted list of non-overlapping intervals of East Asian Ambiguous
-     * characters, generated with:
-     * "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
-    static struct interval ambiguous[] = {
-	{0x00A1, 0x00A1}, {0x00A4, 0x00A4}, {0x00A7, 0x00A8},
-	{0x00AA, 0x00AA}, {0x00AE, 0x00AE}, {0x00B0, 0x00B4},
-	{0x00B6, 0x00BA}, {0x00BC, 0x00BF}, {0x00C6, 0x00C6},
-	{0x00D0, 0x00D0}, {0x00D7, 0x00D8}, {0x00DE, 0x00E1},
-	{0x00E6, 0x00E6}, {0x00E8, 0x00EA}, {0x00EC, 0x00ED},
-	{0x00F0, 0x00F0}, {0x00F2, 0x00F3}, {0x00F7, 0x00FA},
-	{0x00FC, 0x00FC}, {0x00FE, 0x00FE}, {0x0101, 0x0101},
-	{0x0111, 0x0111}, {0x0113, 0x0113}, {0x011B, 0x011B},
-	{0x0126, 0x0127}, {0x012B, 0x012B}, {0x0131, 0x0133},
-	{0x0138, 0x0138}, {0x013F, 0x0142}, {0x0144, 0x0144},
-	{0x0148, 0x014B}, {0x014D, 0x014D}, {0x0152, 0x0153},
-	{0x0166, 0x0167}, {0x016B, 0x016B}, {0x01CE, 0x01CE},
-	{0x01D0, 0x01D0}, {0x01D2, 0x01D2}, {0x01D4, 0x01D4},
-	{0x01D6, 0x01D6}, {0x01D8, 0x01D8}, {0x01DA, 0x01DA},
-	{0x01DC, 0x01DC}, {0x0251, 0x0251}, {0x0261, 0x0261},
-	{0x02C4, 0x02C4}, {0x02C7, 0x02C7}, {0x02C9, 0x02CB},
-	{0x02CD, 0x02CD}, {0x02D0, 0x02D0}, {0x02D8, 0x02DB},
-	{0x02DD, 0x02DD}, {0x02DF, 0x02DF}, {0x0391, 0x03A1},
-	{0x03A3, 0x03A9}, {0x03B1, 0x03C1}, {0x03C3, 0x03C9},
-	{0x0401, 0x0401}, {0x0410, 0x044F}, {0x0451, 0x0451},
-	{0x2010, 0x2010}, {0x2013, 0x2016}, {0x2018, 0x2019},
-	{0x201C, 0x201D}, {0x2020, 0x2022}, {0x2024, 0x2027},
-	{0x2030, 0x2030}, {0x2032, 0x2033}, {0x2035, 0x2035},
-	{0x203B, 0x203B}, {0x203E, 0x203E}, {0x2074, 0x2074},
-	{0x207F, 0x207F}, {0x2081, 0x2084}, {0x20AC, 0x20AC},
-	{0x2103, 0x2103}, {0x2105, 0x2105}, {0x2109, 0x2109},
-	{0x2113, 0x2113}, {0x2116, 0x2116}, {0x2121, 0x2122},
-	{0x2126, 0x2126}, {0x212B, 0x212B}, {0x2153, 0x2154},
-	{0x215B, 0x215E}, {0x2160, 0x216B}, {0x2170, 0x2179},
-	{0x2190, 0x2199}, {0x21B8, 0x21B9}, {0x21D2, 0x21D2},
-	{0x21D4, 0x21D4}, {0x21E7, 0x21E7}, {0x2200, 0x2200},
-	{0x2202, 0x2203}, {0x2207, 0x2208}, {0x220B, 0x220B},
-	{0x220F, 0x220F}, {0x2211, 0x2211}, {0x2215, 0x2215},
-	{0x221A, 0x221A}, {0x221D, 0x2220}, {0x2223, 0x2223},
-	{0x2225, 0x2225}, {0x2227, 0x222C}, {0x222E, 0x222E},
-	{0x2234, 0x2237}, {0x223C, 0x223D}, {0x2248, 0x2248},
-	{0x224C, 0x224C}, {0x2252, 0x2252}, {0x2260, 0x2261},
-	{0x2264, 0x2267}, {0x226A, 0x226B}, {0x226E, 0x226F},
-	{0x2282, 0x2283}, {0x2286, 0x2287}, {0x2295, 0x2295},
-	{0x2299, 0x2299}, {0x22A5, 0x22A5}, {0x22BF, 0x22BF},
-	{0x2312, 0x2312}, {0x2460, 0x24E9}, {0x24EB, 0x254B},
-	{0x2550, 0x2573}, {0x2580, 0x258F}, {0x2592, 0x2595},
-	{0x25A0, 0x25A1}, {0x25A3, 0x25A9}, {0x25B2, 0x25B3},
-	{0x25B6, 0x25B7}, {0x25BC, 0x25BD}, {0x25C0, 0x25C1},
-	{0x25C6, 0x25C8}, {0x25CB, 0x25CB}, {0x25CE, 0x25D1},
-	{0x25E2, 0x25E5}, {0x25EF, 0x25EF}, {0x2605, 0x2606},
-	{0x2609, 0x2609}, {0x260E, 0x260F}, {0x2614, 0x2615},
-	{0x261C, 0x261C}, {0x261E, 0x261E}, {0x2640, 0x2640},
-	{0x2642, 0x2642}, {0x2660, 0x2661}, {0x2663, 0x2665},
-	{0x2667, 0x266A}, {0x266C, 0x266D}, {0x266F, 0x266F},
-	{0x273D, 0x273D}, {0x2776, 0x277F}, {0xE000, 0xF8FF},
-	{0xFFFD, 0xFFFD}, /* {0xF0000, 0xFFFFD}, {0x100000, 0x10FFFD} */
+    /* Sorted list of non-overlapping intervals of East Asian Ambiguous
+     * characters, generated with ../runtime/tools/unicode.vim. */
+    static struct interval ambiguous[] =
+    {
+	{0x00a1, 0x00a1},
+	{0x00a4, 0x00a4},
+	{0x00a7, 0x00a8},
+	{0x00aa, 0x00aa},
+	{0x00ad, 0x00ae},
+	{0x00b0, 0x00b4},
+	{0x00b6, 0x00ba},
+	{0x00bc, 0x00bf},
+	{0x00c6, 0x00c6},
+	{0x00d0, 0x00d0},
+	{0x00d7, 0x00d8},
+	{0x00de, 0x00e1},
+	{0x00e6, 0x00e6},
+	{0x00e8, 0x00ea},
+	{0x00ec, 0x00ed},
+	{0x00f0, 0x00f0},
+	{0x00f2, 0x00f3},
+	{0x00f7, 0x00fa},
+	{0x00fc, 0x00fc},
+	{0x00fe, 0x00fe},
+	{0x0101, 0x0101},
+	{0x0111, 0x0111},
+	{0x0113, 0x0113},
+	{0x011b, 0x011b},
+	{0x0126, 0x0127},
+	{0x012b, 0x012b},
+	{0x0131, 0x0133},
+	{0x0138, 0x0138},
+	{0x013f, 0x0142},
+	{0x0144, 0x0144},
+	{0x0148, 0x014b},
+	{0x014d, 0x014d},
+	{0x0152, 0x0153},
+	{0x0166, 0x0167},
+	{0x016b, 0x016b},
+	{0x01ce, 0x01ce},
+	{0x01d0, 0x01d0},
+	{0x01d2, 0x01d2},
+	{0x01d4, 0x01d4},
+	{0x01d6, 0x01d6},
+	{0x01d8, 0x01d8},
+	{0x01da, 0x01da},
+	{0x01dc, 0x01dc},
+	{0x0251, 0x0251},
+	{0x0261, 0x0261},
+	{0x02c4, 0x02c4},
+	{0x02c7, 0x02c7},
+	{0x02c9, 0x02cb},
+	{0x02cd, 0x02cd},
+	{0x02d0, 0x02d0},
+	{0x02d8, 0x02db},
+	{0x02dd, 0x02dd},
+	{0x02df, 0x02df},
+	{0x0391, 0x03a1},
+	{0x03a3, 0x03a9},
+	{0x03b1, 0x03c1},
+	{0x03c3, 0x03c9},
+	{0x0401, 0x0401},
+	{0x0410, 0x044f},
+	{0x0451, 0x0451},
+	{0x2010, 0x2010},
+	{0x2013, 0x2016},
+	{0x2018, 0x2019},
+	{0x201c, 0x201d},
+	{0x2020, 0x2022},
+	{0x2024, 0x2027},
+	{0x2030, 0x2030},
+	{0x2032, 0x2033},
+	{0x2035, 0x2035},
+	{0x203b, 0x203b},
+	{0x203e, 0x203e},
+	{0x2074, 0x2074},
+	{0x207f, 0x207f},
+	{0x2081, 0x2084},
+	{0x20ac, 0x20ac},
+	{0x2103, 0x2103},
+	{0x2105, 0x2105},
+	{0x2109, 0x2109},
+	{0x2113, 0x2113},
+	{0x2116, 0x2116},
+	{0x2121, 0x2122},
+	{0x2126, 0x2126},
+	{0x212b, 0x212b},
+	{0x2153, 0x2154},
+	{0x215b, 0x215e},
+	{0x2160, 0x216b},
+	{0x2170, 0x2179},
+	{0x2189, 0x2189},
+	{0x2190, 0x2199},
+	{0x21b8, 0x21b9},
+	{0x21d2, 0x21d2},
+	{0x21d4, 0x21d4},
+	{0x21e7, 0x21e7},
+	{0x2200, 0x2200},
+	{0x2202, 0x2203},
+	{0x2207, 0x2208},
+	{0x220b, 0x220b},
+	{0x220f, 0x220f},
+	{0x2211, 0x2211},
+	{0x2215, 0x2215},
+	{0x221a, 0x221a},
+	{0x221d, 0x2220},
+	{0x2223, 0x2223},
+	{0x2225, 0x2225},
+	{0x2227, 0x222c},
+	{0x222e, 0x222e},
+	{0x2234, 0x2237},
+	{0x223c, 0x223d},
+	{0x2248, 0x2248},
+	{0x224c, 0x224c},
+	{0x2252, 0x2252},
+	{0x2260, 0x2261},
+	{0x2264, 0x2267},
+	{0x226a, 0x226b},
+	{0x226e, 0x226f},
+	{0x2282, 0x2283},
+	{0x2286, 0x2287},
+	{0x2295, 0x2295},
+	{0x2299, 0x2299},
+	{0x22a5, 0x22a5},
+	{0x22bf, 0x22bf},
+	{0x2312, 0x2312},
+	{0x2460, 0x24e9},
+	{0x24eb, 0x254b},
+	{0x2550, 0x2573},
+	{0x2580, 0x258f},
+	{0x2592, 0x2595},
+	{0x25a0, 0x25a1},
+	{0x25a3, 0x25a9},
+	{0x25b2, 0x25b3},
+	{0x25b6, 0x25b7},
+	{0x25bc, 0x25bd},
+	{0x25c0, 0x25c1},
+	{0x25c6, 0x25c8},
+	{0x25cb, 0x25cb},
+	{0x25ce, 0x25d1},
+	{0x25e2, 0x25e5},
+	{0x25ef, 0x25ef},
+	{0x2605, 0x2606},
+	{0x2609, 0x2609},
+	{0x260e, 0x260f},
+	{0x2614, 0x2615},
+	{0x261c, 0x261c},
+	{0x261e, 0x261e},
+	{0x2640, 0x2640},
+	{0x2642, 0x2642},
+	{0x2660, 0x2661},
+	{0x2663, 0x2665},
+	{0x2667, 0x266a},
+	{0x266c, 0x266d},
+	{0x266f, 0x266f},
+	{0x269e, 0x269f},
+	{0x26be, 0x26bf},
+	{0x26c4, 0x26cd},
+	{0x26cf, 0x26e1},
+	{0x26e3, 0x26e3},
+	{0x26e8, 0x26ff},
+	{0x273d, 0x273d},
+	{0x2757, 0x2757},
+	{0x2776, 0x277f},
+	{0x2b55, 0x2b59},
+	{0x3248, 0x324f},
+	{0xe000, 0xf8ff},
+	{0xfffd, 0xfffd},
+	{0x1f100, 0x1f10a},
+	{0x1f110, 0x1f12d},
+	{0x1f131, 0x1f131},
+	{0x1f13d, 0x1f13d},
+	{0x1f13f, 0x1f13f},
+	{0x1f142, 0x1f142},
+	{0x1f146, 0x1f146},
+	{0x1f14a, 0x1f14e},
+	{0x1f157, 0x1f157},
+	{0x1f15f, 0x1f15f},
+	{0x1f179, 0x1f179},
+	{0x1f17b, 0x1f17c},
+	{0x1f17f, 0x1f17f},
+	{0x1f18a, 0x1f18d},
+	{0x1f190, 0x1f190},
+	{0xf0000, 0xffffd},
+	{0x100000, 0x10fffd}
     };
 
     if (c >= 0x100)
@@ -1807,7 +1936,7 @@ utfc_ptr2len(p)
 	return 1;
 
     /*
-     * Check for composing characters.  We can handle only the first two, but
+     * Check for composing characters.  We can handle only the first six, but
      * skip all of them (otherwise the cursor would get stuck).
      */
 #ifdef FEAT_ARABIC
@@ -1855,7 +1984,7 @@ utfc_ptr2len_len(p, size)
 	return 1;
 
     /*
-     * Check for composing characters.  We can handle only the first two, but
+     * Check for composing characters.  We can handle only the first six, but
      * skip all of them (otherwise the cursor would get stuck).
      */
 #ifdef FEAT_ARABIC
@@ -1973,38 +2102,198 @@ utf_char2bytes(c, buf)
 utf_iscomposing(c)
     int		c;
 {
-    /* sorted list of non-overlapping intervals */
+    /* Sorted list of non-overlapping intervals.
+     * Generated by ../runtime/tools/unicode.vim. */
     static struct interval combining[] =
     {
-	{0x0300, 0x034f}, {0x0360, 0x036f}, {0x0483, 0x0486}, {0x0488, 0x0489},
-	{0x0591, 0x05a1}, {0x05a3, 0x05b9}, {0x05bb, 0x05bd}, {0x05bf, 0x05bf},
-	{0x05c1, 0x05c2}, {0x05c4, 0x05c4}, {0x0610, 0x0615}, {0x064b, 0x0658},
-	{0x0670, 0x0670}, {0x06d6, 0x06dc}, {0x06de, 0x06e4}, {0x06e7, 0x06e8},
-	{0x06ea, 0x06ed}, {0x0711, 0x0711}, {0x0730, 0x074a}, {0x07a6, 0x07b0},
-	{0x0901, 0x0903}, {0x093c, 0x093c}, {0x093e, 0x094d}, {0x0951, 0x0954},
-	{0x0962, 0x0963}, {0x0981, 0x0983}, {0x09bc, 0x09bc}, {0x09be, 0x09c4},
-	{0x09c7, 0x09c8}, {0x09cb, 0x09cd}, {0x09d7, 0x09d7}, {0x09e2, 0x09e3},
-	{0x0a01, 0x0a03}, {0x0a3c, 0x0a3c}, {0x0a3e, 0x0a42}, {0x0a47, 0x0a48},
-	{0x0a4b, 0x0a4d}, {0x0a70, 0x0a71}, {0x0a81, 0x0a83}, {0x0abc, 0x0abc},
-	{0x0abe, 0x0ac5}, {0x0ac7, 0x0ac9}, {0x0acb, 0x0acd}, {0x0ae2, 0x0ae3},
-	{0x0b01, 0x0b03}, {0x0b3c, 0x0b3c}, {0x0b3e, 0x0b43}, {0x0b47, 0x0b48},
-	{0x0b4b, 0x0b4d}, {0x0b56, 0x0b57}, {0x0b82, 0x0b82}, {0x0bbe, 0x0bc2},
-	{0x0bc6, 0x0bc8}, {0x0bca, 0x0bcd}, {0x0bd7, 0x0bd7}, {0x0c01, 0x0c03},
-	{0x0c3e, 0x0c44}, {0x0c46, 0x0c48}, {0x0c4a, 0x0c4d}, {0x0c55, 0x0c56},
-	{0x0c82, 0x0c83}, {0x0cbc, 0x0cbc}, {0x0cbe, 0x0cc4}, {0x0cc6, 0x0cc8},
-	{0x0cca, 0x0ccd}, {0x0cd5, 0x0cd6}, {0x0d02, 0x0d03}, {0x0d3e, 0x0d43},
-	{0x0d46, 0x0d48}, {0x0d4a, 0x0d4d}, {0x0d57, 0x0d57}, {0x0d82, 0x0d83},
-	{0x0dca, 0x0dca}, {0x0dcf, 0x0dd4}, {0x0dd6, 0x0dd6}, {0x0dd8, 0x0ddf},
-	{0x0df2, 0x0df3}, {0x0e31, 0x0e31}, {0x0e34, 0x0e3a}, {0x0e47, 0x0e4e},
-	{0x0eb1, 0x0eb1}, {0x0eb4, 0x0eb9}, {0x0ebb, 0x0ebc}, {0x0ec8, 0x0ecd},
-	{0x0f18, 0x0f19}, {0x0f35, 0x0f35}, {0x0f37, 0x0f37}, {0x0f39, 0x0f39},
-	{0x0f3e, 0x0f3f}, {0x0f71, 0x0f84}, {0x0f86, 0x0f87}, {0x0f90, 0x0f97},
-	{0x0f99, 0x0fbc}, {0x0fc6, 0x0fc6}, {0x102c, 0x1032}, {0x1036, 0x1039},
-	{0x1056, 0x1059}, {0x1712, 0x1714}, {0x1732, 0x1734}, {0x1752, 0x1753},
-	{0x1772, 0x1773}, {0x17b6, 0x17d3}, {0x17dd, 0x17dd}, {0x180b, 0x180d},
-	{0x18a9, 0x18a9}, {0x1920, 0x192b}, {0x1930, 0x193b}, {0x20d0, 0x20ea},
-	{0x302a, 0x302f}, {0x3099, 0x309a}, {0xfb1e, 0xfb1e}, {0xfe00, 0xfe0f},
-	{0xfe20, 0xfe23},
+	{0x0300, 0x036f},
+	{0x0483, 0x0489},
+	{0x0591, 0x05bd},
+	{0x05bf, 0x05bf},
+	{0x05c1, 0x05c2},
+	{0x05c4, 0x05c5},
+	{0x05c7, 0x05c7},
+	{0x0610, 0x061a},
+	{0x064b, 0x065e},
+	{0x0670, 0x0670},
+	{0x06d6, 0x06dc},
+	{0x06de, 0x06e4},
+	{0x06e7, 0x06e8},
+	{0x06ea, 0x06ed},
+	{0x0711, 0x0711},
+	{0x0730, 0x074a},
+	{0x07a6, 0x07b0},
+	{0x07eb, 0x07f3},
+	{0x0816, 0x0819},
+	{0x081b, 0x0823},
+	{0x0825, 0x0827},
+	{0x0829, 0x082d},
+	{0x0900, 0x0903},
+	{0x093c, 0x093c},
+	{0x093e, 0x094e},
+	{0x0951, 0x0955},
+	{0x0962, 0x0963},
+	{0x0981, 0x0983},
+	{0x09bc, 0x09bc},
+	{0x09be, 0x09c4},
+	{0x09c7, 0x09c8},
+	{0x09cb, 0x09cd},
+	{0x09d7, 0x09d7},
+	{0x09e2, 0x09e3},
+	{0x0a01, 0x0a03},
+	{0x0a3c, 0x0a3c},
+	{0x0a3e, 0x0a42},
+	{0x0a47, 0x0a48},
+	{0x0a4b, 0x0a4d},
+	{0x0a51, 0x0a51},
+	{0x0a70, 0x0a71},
+	{0x0a75, 0x0a75},
+	{0x0a81, 0x0a83},
+	{0x0abc, 0x0abc},
+	{0x0abe, 0x0ac5},
+	{0x0ac7, 0x0ac9},
+	{0x0acb, 0x0acd},
+	{0x0ae2, 0x0ae3},
+	{0x0b01, 0x0b03},
+	{0x0b3c, 0x0b3c},
+	{0x0b3e, 0x0b44},
+	{0x0b47, 0x0b48},
+	{0x0b4b, 0x0b4d},
+	{0x0b56, 0x0b57},
+	{0x0b62, 0x0b63},
+	{0x0b82, 0x0b82},
+	{0x0bbe, 0x0bc2},
+	{0x0bc6, 0x0bc8},
+	{0x0bca, 0x0bcd},
+	{0x0bd7, 0x0bd7},
+	{0x0c01, 0x0c03},
+	{0x0c3e, 0x0c44},
+	{0x0c46, 0x0c48},
+	{0x0c4a, 0x0c4d},
+	{0x0c55, 0x0c56},
+	{0x0c62, 0x0c63},
+	{0x0c82, 0x0c83},
+	{0x0cbc, 0x0cbc},
+	{0x0cbe, 0x0cc4},
+	{0x0cc6, 0x0cc8},
+	{0x0cca, 0x0ccd},
+	{0x0cd5, 0x0cd6},
+	{0x0ce2, 0x0ce3},
+	{0x0d02, 0x0d03},
+	{0x0d3e, 0x0d44},
+	{0x0d46, 0x0d48},
+	{0x0d4a, 0x0d4d},
+	{0x0d57, 0x0d57},
+	{0x0d62, 0x0d63},
+	{0x0d82, 0x0d83},
+	{0x0dca, 0x0dca},
+	{0x0dcf, 0x0dd4},
+	{0x0dd6, 0x0dd6},
+	{0x0dd8, 0x0ddf},
+	{0x0df2, 0x0df3},
+	{0x0e31, 0x0e31},
+	{0x0e34, 0x0e3a},
+	{0x0e47, 0x0e4e},
+	{0x0eb1, 0x0eb1},
+	{0x0eb4, 0x0eb9},
+	{0x0ebb, 0x0ebc},
+	{0x0ec8, 0x0ecd},
+	{0x0f18, 0x0f19},
+	{0x0f35, 0x0f35},
+	{0x0f37, 0x0f37},
+	{0x0f39, 0x0f39},
+	{0x0f3e, 0x0f3f},
+	{0x0f71, 0x0f84},
+	{0x0f86, 0x0f87},
+	{0x0f90, 0x0f97},
+	{0x0f99, 0x0fbc},
+	{0x0fc6, 0x0fc6},
+	{0x102b, 0x103e},
+	{0x1056, 0x1059},
+	{0x105e, 0x1060},
+	{0x1062, 0x1064},
+	{0x1067, 0x106d},
+	{0x1071, 0x1074},
+	{0x1082, 0x108d},
+	{0x108f, 0x108f},
+	{0x109a, 0x109d},
+	{0x135f, 0x135f},
+	{0x1712, 0x1714},
+	{0x1732, 0x1734},
+	{0x1752, 0x1753},
+	{0x1772, 0x1773},
+	{0x17b6, 0x17d3},
+	{0x17dd, 0x17dd},
+	{0x180b, 0x180d},
+	{0x18a9, 0x18a9},
+	{0x1920, 0x192b},
+	{0x1930, 0x193b},
+	{0x19b0, 0x19c0},
+	{0x19c8, 0x19c9},
+	{0x1a17, 0x1a1b},
+	{0x1a55, 0x1a5e},
+	{0x1a60, 0x1a7c},
+	{0x1a7f, 0x1a7f},
+	{0x1b00, 0x1b04},
+	{0x1b34, 0x1b44},
+	{0x1b6b, 0x1b73},
+	{0x1b80, 0x1b82},
+	{0x1ba1, 0x1baa},
+	{0x1c24, 0x1c37},
+	{0x1cd0, 0x1cd2},
+	{0x1cd4, 0x1ce8},
+	{0x1ced, 0x1ced},
+	{0x1cf2, 0x1cf2},
+	{0x1dc0, 0x1de6},
+	{0x1dfd, 0x1dff},
+	{0x20d0, 0x20f0},
+	{0x2cef, 0x2cf1},
+	{0x2de0, 0x2dff},
+	{0x302a, 0x302f},
+	{0x3099, 0x309a},
+	{0xa66f, 0xa672},
+	{0xa67c, 0xa67d},
+	{0xa6f0, 0xa6f1},
+	{0xa802, 0xa802},
+	{0xa806, 0xa806},
+	{0xa80b, 0xa80b},
+	{0xa823, 0xa827},
+	{0xa880, 0xa881},
+	{0xa8b4, 0xa8c4},
+	{0xa8e0, 0xa8f1},
+	{0xa926, 0xa92d},
+	{0xa947, 0xa953},
+	{0xa980, 0xa983},
+	{0xa9b3, 0xa9c0},
+	{0xaa29, 0xaa36},
+	{0xaa43, 0xaa43},
+	{0xaa4c, 0xaa4d},
+	{0xaa7b, 0xaa7b},
+	{0xaab0, 0xaab0},
+	{0xaab2, 0xaab4},
+	{0xaab7, 0xaab8},
+	{0xaabe, 0xaabf},
+	{0xaac1, 0xaac1},
+	{0xabe3, 0xabea},
+	{0xabec, 0xabed},
+	{0xfb1e, 0xfb1e},
+	{0xfe00, 0xfe0f},
+	{0xfe20, 0xfe26},
+	{0x101fd, 0x101fd},
+	{0x10a01, 0x10a03},
+	{0x10a05, 0x10a06},
+	{0x10a0c, 0x10a0f},
+	{0x10a38, 0x10a3a},
+	{0x10a3f, 0x10a3f},
+	{0x11080, 0x11082},
+	{0x110b0, 0x110ba},
+	{0x1d165, 0x1d169},
+	{0x1d16d, 0x1d172},
+	{0x1d17b, 0x1d182},
+	{0x1d185, 0x1d18b},
+	{0x1d1aa, 0x1d1ad},
+	{0x1d242, 0x1d244},
+	{0xe0100, 0xe01ef}
     };
 
     return intable(combining, sizeof(combining), c);
@@ -2152,15 +2441,16 @@ utf_class(c)
  * Code for Unicode case-dependent operations.  Based on notes in
  * http://www.unicode.org/Public/UNIDATA/CaseFolding.txt
  * This code uses simple case folding, not full case folding.
+ * Last updated for Unicode 5.2.
  */
 
 /*
- * The following table is built by foldExtract.pl < CaseFolding.txt .
- * It must be in numeric order, because we use binary search on it.
- * An entry such as {0x41,0x5a,1,32} means that UCS-4 characters in the range
- * from 0x41 to 0x5a inclusive, stepping by 1, are folded by adding 32.
+ * The following tables are built by ../runtime/tools/unicode.vim.
+ * They must be in numeric order, because we use binary search.
+ * An entry such as {0x41,0x5a,1,32} means that Unicode characters in the
+ * range from 0x41 to 0x5a inclusive, stepping by 1, are changed to
+ * folded/upper/lower by adding 32.
  */
-
 typedef struct
 {
     int rangeStart;
@@ -2171,41 +2461,161 @@ typedef struct
 
 static convertStruct foldCase[] =
 {
-	{0x41,0x5a,1,32}, {0xc0,0xd6,1,32}, {0xd8,0xde,1,32},
-	{0x100,0x12e,2,1}, {0x130,0x130,-1,-199}, {0x132,0x136,2,1},
-	{0x139,0x147,2,1}, {0x14a,0x176,2,1}, {0x178,0x178,-1,-121},
-	{0x179,0x17d,2,1}, {0x181,0x181,-1,210}, {0x182,0x184,2,1},
-	{0x186,0x186,-1,206}, {0x187,0x187,-1,1}, {0x189,0x18a,1,205},
-	{0x18b,0x18b,-1,1}, {0x18e,0x18e,-1,79}, {0x18f,0x18f,-1,202},
-	{0x190,0x190,-1,203}, {0x191,0x191,-1,1}, {0x193,0x193,-1,205},
-	{0x194,0x194,-1,207}, {0x196,0x196,-1,211}, {0x197,0x197,-1,209},
-	{0x198,0x198,-1,1}, {0x19c,0x19c,-1,211}, {0x19d,0x19d,-1,213},
-	{0x19f,0x19f,-1,214}, {0x1a0,0x1a4,2,1}, {0x1a6,0x1a6,-1,218},
-	{0x1a7,0x1a7,-1,1}, {0x1a9,0x1a9,-1,218}, {0x1ac,0x1ac,-1,1},
-	{0x1ae,0x1ae,-1,218}, {0x1af,0x1af,-1,1}, {0x1b1,0x1b2,1,217},
-	{0x1b3,0x1b5,2,1}, {0x1b7,0x1b7,-1,219}, {0x1b8,0x1bc,4,1},
-	{0x1c4,0x1c4,-1,2}, {0x1c5,0x1c5,-1,1}, {0x1c7,0x1c7,-1,2},
-	{0x1c8,0x1c8,-1,1}, {0x1ca,0x1ca,-1,2}, {0x1cb,0x1db,2,1},
-	{0x1de,0x1ee,2,1}, {0x1f1,0x1f1,-1,2}, {0x1f2,0x1f4,2,1},
-	{0x1f6,0x1f6,-1,-97}, {0x1f7,0x1f7,-1,-56}, {0x1f8,0x21e,2,1},
-	{0x220,0x220,-1,-130}, {0x222,0x232,2,1}, {0x386,0x386,-1,38},
-	{0x388,0x38a,1,37}, {0x38c,0x38c,-1,64}, {0x38e,0x38f,1,63},
-	{0x391,0x3a1,1,32}, {0x3a3,0x3ab,1,32}, {0x3d8,0x3ee,2,1},
-	{0x3f4,0x3f4,-1,-60}, {0x3f7,0x3f7,-1,1}, {0x3f9,0x3f9,-1,-7},
-	{0x3fa,0x3fa,-1,1}, {0x400,0x40f,1,80}, {0x410,0x42f,1,32},
-	{0x460,0x480,2,1}, {0x48a,0x4be,2,1}, {0x4c1,0x4cd,2,1},
-	{0x4d0,0x4f4,2,1}, {0x4f8,0x500,8,1}, {0x502,0x50e,2,1},
-	{0x531,0x556,1,48}, {0x1e00,0x1e94,2,1}, {0x1ea0,0x1ef8,2,1},
-	{0x1f08,0x1f0f,1,-8}, {0x1f18,0x1f1d,1,-8}, {0x1f28,0x1f2f,1,-8},
-	{0x1f38,0x1f3f,1,-8}, {0x1f48,0x1f4d,1,-8}, {0x1f59,0x1f5f,2,-8},
-	{0x1f68,0x1f6f,1,-8}, {0x1f88,0x1f8f,1,-8}, {0x1f98,0x1f9f,1,-8},
-	{0x1fa8,0x1faf,1,-8}, {0x1fb8,0x1fb9,1,-8}, {0x1fba,0x1fbb,1,-74},
-	{0x1fbc,0x1fbc,-1,-9}, {0x1fc8,0x1fcb,1,-86}, {0x1fcc,0x1fcc,-1,-9},
-	{0x1fd8,0x1fd9,1,-8}, {0x1fda,0x1fdb,1,-100}, {0x1fe8,0x1fe9,1,-8},
-	{0x1fea,0x1feb,1,-112}, {0x1fec,0x1fec,-1,-7}, {0x1ff8,0x1ff9,1,-128},
-	{0x1ffa,0x1ffb,1,-126}, {0x1ffc,0x1ffc,-1,-9}, {0x2126,0x2126,-1,-7517},
-	{0x212a,0x212a,-1,-8383}, {0x212b,0x212b,-1,-8262},
-	{0x2160,0x216f,1,16}, {0x24b6,0x24cf,1,26}, {0xff21,0xff3a,1,32},
+	{0x41,0x5a,1,32},
+	{0xb5,0xb5,-1,775},
+	{0xc0,0xd6,1,32},
+	{0xd8,0xde,1,32},
+	{0x100,0x12e,2,1},
+	{0x132,0x136,2,1},
+	{0x139,0x147,2,1},
+	{0x14a,0x176,2,1},
+	{0x178,0x178,-1,-121},
+	{0x179,0x17d,2,1},
+	{0x17f,0x17f,-1,-268},
+	{0x181,0x181,-1,210},
+	{0x182,0x184,2,1},
+	{0x186,0x186,-1,206},
+	{0x187,0x187,-1,1},
+	{0x189,0x18a,1,205},
+	{0x18b,0x18b,-1,1},
+	{0x18e,0x18e,-1,79},
+	{0x18f,0x18f,-1,202},
+	{0x190,0x190,-1,203},
+	{0x191,0x191,-1,1},
+	{0x193,0x193,-1,205},
+	{0x194,0x194,-1,207},
+	{0x196,0x196,-1,211},
+	{0x197,0x197,-1,209},
+	{0x198,0x198,-1,1},
+	{0x19c,0x19c,-1,211},
+	{0x19d,0x19d,-1,213},
+	{0x19f,0x19f,-1,214},
+	{0x1a0,0x1a4,2,1},
+	{0x1a6,0x1a6,-1,218},
+	{0x1a7,0x1a7,-1,1},
+	{0x1a9,0x1a9,-1,218},
+	{0x1ac,0x1ac,-1,1},
+	{0x1ae,0x1ae,-1,218},
+	{0x1af,0x1af,-1,1},
+	{0x1b1,0x1b2,1,217},
+	{0x1b3,0x1b5,2,1},
+	{0x1b7,0x1b7,-1,219},
+	{0x1b8,0x1bc,4,1},
+	{0x1c4,0x1c4,-1,2},
+	{0x1c5,0x1c5,-1,1},
+	{0x1c7,0x1c7,-1,2},
+	{0x1c8,0x1c8,-1,1},
+	{0x1ca,0x1ca,-1,2},
+	{0x1cb,0x1db,2,1},
+	{0x1de,0x1ee,2,1},
+	{0x1f1,0x1f1,-1,2},
+	{0x1f2,0x1f4,2,1},
+	{0x1f6,0x1f6,-1,-97},
+	{0x1f7,0x1f7,-1,-56},
+	{0x1f8,0x21e,2,1},
+	{0x220,0x220,-1,-130},
+	{0x222,0x232,2,1},
+	{0x23a,0x23a,-1,10795},
+	{0x23b,0x23b,-1,1},
+	{0x23d,0x23d,-1,-163},
+	{0x23e,0x23e,-1,10792},
+	{0x241,0x241,-1,1},
+	{0x243,0x243,-1,-195},
+	{0x244,0x244,-1,69},
+	{0x245,0x245,-1,71},
+	{0x246,0x24e,2,1},
+	{0x345,0x345,-1,116},
+	{0x370,0x372,2,1},
+	{0x376,0x376,-1,1},
+	{0x386,0x386,-1,38},
+	{0x388,0x38a,1,37},
+	{0x38c,0x38c,-1,64},
+	{0x38e,0x38f,1,63},
+	{0x391,0x3a1,1,32},
+	{0x3a3,0x3ab,1,32},
+	{0x3c2,0x3c2,-1,1},
+	{0x3cf,0x3cf,-1,8},
+	{0x3d0,0x3d0,-1,-30},
+	{0x3d1,0x3d1,-1,-25},
+	{0x3d5,0x3d5,-1,-15},
+	{0x3d6,0x3d6,-1,-22},
+	{0x3d8,0x3ee,2,1},
+	{0x3f0,0x3f0,-1,-54},
+	{0x3f1,0x3f1,-1,-48},
+	{0x3f4,0x3f4,-1,-60},
+	{0x3f5,0x3f5,-1,-64},
+	{0x3f7,0x3f7,-1,1},
+	{0x3f9,0x3f9,-1,-7},
+	{0x3fa,0x3fa,-1,1},
+	{0x3fd,0x3ff,1,-130},
+	{0x400,0x40f,1,80},
+	{0x410,0x42f,1,32},
+	{0x460,0x480,2,1},
+	{0x48a,0x4be,2,1},
+	{0x4c0,0x4c0,-1,15},
+	{0x4c1,0x4cd,2,1},
+	{0x4d0,0x524,2,1},
+	{0x531,0x556,1,48},
+	{0x10a0,0x10c5,1,7264},
+	{0x1e00,0x1e94,2,1},
+	{0x1e9b,0x1e9b,-1,-58},
+	{0x1e9e,0x1e9e,-1,-7615},
+	{0x1ea0,0x1efe,2,1},
+	{0x1f08,0x1f0f,1,-8},
+	{0x1f18,0x1f1d,1,-8},
+	{0x1f28,0x1f2f,1,-8},
+	{0x1f38,0x1f3f,1,-8},
+	{0x1f48,0x1f4d,1,-8},
+	{0x1f59,0x1f5f,2,-8},
+	{0x1f68,0x1f6f,1,-8},
+	{0x1f88,0x1f8f,1,-8},
+	{0x1f98,0x1f9f,1,-8},
+	{0x1fa8,0x1faf,1,-8},
+	{0x1fb8,0x1fb9,1,-8},
+	{0x1fba,0x1fbb,1,-74},
+	{0x1fbc,0x1fbc,-1,-9},
+	{0x1fbe,0x1fbe,-1,-7173},
+	{0x1fc8,0x1fcb,1,-86},
+	{0x1fcc,0x1fcc,-1,-9},
+	{0x1fd8,0x1fd9,1,-8},
+	{0x1fda,0x1fdb,1,-100},
+	{0x1fe8,0x1fe9,1,-8},
+	{0x1fea,0x1feb,1,-112},
+	{0x1fec,0x1fec,-1,-7},
+	{0x1ff8,0x1ff9,1,-128},
+	{0x1ffa,0x1ffb,1,-126},
+	{0x1ffc,0x1ffc,-1,-9},
+	{0x2126,0x2126,-1,-7517},
+	{0x212a,0x212a,-1,-8383},
+	{0x212b,0x212b,-1,-8262},
+	{0x2132,0x2132,-1,28},
+	{0x2160,0x216f,1,16},
+	{0x2183,0x2183,-1,1},
+	{0x24b6,0x24cf,1,26},
+	{0x2c00,0x2c2e,1,48},
+	{0x2c60,0x2c60,-1,1},
+	{0x2c62,0x2c62,-1,-10743},
+	{0x2c63,0x2c63,-1,-3814},
+	{0x2c64,0x2c64,-1,-10727},
+	{0x2c67,0x2c6b,2,1},
+	{0x2c6d,0x2c6d,-1,-10780},
+	{0x2c6e,0x2c6e,-1,-10749},
+	{0x2c6f,0x2c6f,-1,-10783},
+	{0x2c70,0x2c70,-1,-10782},
+	{0x2c72,0x2c75,3,1},
+	{0x2c7e,0x2c7f,1,-10815},
+	{0x2c80,0x2ce2,2,1},
+	{0x2ceb,0x2ced,2,1},
+	{0xa640,0xa65e,2,1},
+	{0xa662,0xa66c,2,1},
+	{0xa680,0xa696,2,1},
+	{0xa722,0xa72e,2,1},
+	{0xa732,0xa76e,2,1},
+	{0xa779,0xa77b,2,1},
+	{0xa77d,0xa77d,-1,-35332},
+	{0xa77e,0xa786,2,1},
+	{0xa78b,0xa78b,-1,1},
+	{0xff21,0xff3a,1,32},
 	{0x10400,0x10427,1,40}
 };
 
@@ -2253,85 +2663,306 @@ utf_fold(a)
     return utf_convert(a, foldCase, sizeof(foldCase));
 }
 
-/*
- * The following tables are built by upperLowerExtract.pl < UnicodeData.txt .
- * They must be in numeric order, because we use binary search on them.
- * An entry such as {0x41,0x5a,1,32} means that UCS-4 characters in the range
- * from 0x41 to 0x5a inclusive, stepping by 1, are switched to lower (for
- * example) by adding 32.
- */
 static convertStruct toLower[] =
 {
-	{0x41,0x5a,1,32}, {0xc0,0xd6,1,32}, {0xd8,0xde,1,32},
-	{0x100,0x12e,2,1}, {0x130,0x130,-1,-199}, {0x132,0x136,2,1},
-	{0x139,0x147,2,1}, {0x14a,0x176,2,1}, {0x178,0x178,-1,-121},
-	{0x179,0x17d,2,1}, {0x181,0x181,-1,210}, {0x182,0x184,2,1},
-	{0x186,0x186,-1,206}, {0x187,0x187,-1,1}, {0x189,0x18a,1,205},
-	{0x18b,0x18b,-1,1}, {0x18e,0x18e,-1,79}, {0x18f,0x18f,-1,202},
-	{0x190,0x190,-1,203}, {0x191,0x191,-1,1}, {0x193,0x193,-1,205},
-	{0x194,0x194,-1,207}, {0x196,0x196,-1,211}, {0x197,0x197,-1,209},
-	{0x198,0x198,-1,1}, {0x19c,0x19c,-1,211}, {0x19d,0x19d,-1,213},
-	{0x19f,0x19f,-1,214}, {0x1a0,0x1a4,2,1}, {0x1a6,0x1a6,-1,218},
-	{0x1a7,0x1a7,-1,1}, {0x1a9,0x1a9,-1,218}, {0x1ac,0x1ac,-1,1},
-	{0x1ae,0x1ae,-1,218}, {0x1af,0x1af,-1,1}, {0x1b1,0x1b2,1,217},
-	{0x1b3,0x1b5,2,1}, {0x1b7,0x1b7,-1,219}, {0x1b8,0x1bc,4,1},
-	{0x1c4,0x1ca,3,2}, {0x1cd,0x1db,2,1}, {0x1de,0x1ee,2,1},
-	{0x1f1,0x1f1,-1,2}, {0x1f4,0x1f4,-1,1}, {0x1f6,0x1f6,-1,-97},
-	{0x1f7,0x1f7,-1,-56}, {0x1f8,0x21e,2,1}, {0x220,0x220,-1,-130},
-	{0x222,0x232,2,1}, {0x386,0x386,-1,38}, {0x388,0x38a,1,37},
-	{0x38c,0x38c,-1,64}, {0x38e,0x38f,1,63}, {0x391,0x3a1,1,32},
-	{0x3a3,0x3ab,1,32}, {0x3d8,0x3ee,2,1}, {0x3f4,0x3f4,-1,-60},
-	{0x3f7,0x3f7,-1,1}, {0x3f9,0x3f9,-1,-7}, {0x3fa,0x3fa,-1,1},
-	{0x400,0x40f,1,80}, {0x410,0x42f,1,32}, {0x460,0x480,2,1},
-	{0x48a,0x4be,2,1}, {0x4c1,0x4cd,2,1}, {0x4d0,0x4f4,2,1},
-	{0x4f8,0x500,8,1}, {0x502,0x50e,2,1}, {0x531,0x556,1,48},
-	{0x1e00,0x1e94,2,1}, {0x1ea0,0x1ef8,2,1}, {0x1f08,0x1f0f,1,-8},
-	{0x1f18,0x1f1d,1,-8}, {0x1f28,0x1f2f,1,-8}, {0x1f38,0x1f3f,1,-8},
-	{0x1f48,0x1f4d,1,-8}, {0x1f59,0x1f5f,2,-8}, {0x1f68,0x1f6f,1,-8},
-	{0x1fb8,0x1fb9,1,-8}, {0x1fba,0x1fbb,1,-74}, {0x1fc8,0x1fcb,1,-86},
-	{0x1fd8,0x1fd9,1,-8}, {0x1fda,0x1fdb,1,-100}, {0x1fe8,0x1fe9,1,-8},
-	{0x1fea,0x1feb,1,-112}, {0x1fec,0x1fec,-1,-7}, {0x1ff8,0x1ff9,1,-128},
-	{0x1ffa,0x1ffb,1,-126}, {0x2126,0x2126,-1,-7517}, {0x212a,0x212a,-1,-8383},
-	{0x212b,0x212b,-1,-8262}, {0xff21,0xff3a,1,32}, {0x10400,0x10427,1,40}
+	{0x41,0x5a,1,32},
+	{0xc0,0xd6,1,32},
+	{0xd8,0xde,1,32},
+	{0x100,0x12e,2,1},
+	{0x130,0x130,-1,-199},
+	{0x132,0x136,2,1},
+	{0x139,0x147,2,1},
+	{0x14a,0x176,2,1},
+	{0x178,0x178,-1,-121},
+	{0x179,0x17d,2,1},
+	{0x181,0x181,-1,210},
+	{0x182,0x184,2,1},
+	{0x186,0x186,-1,206},
+	{0x187,0x187,-1,1},
+	{0x189,0x18a,1,205},
+	{0x18b,0x18b,-1,1},
+	{0x18e,0x18e,-1,79},
+	{0x18f,0x18f,-1,202},
+	{0x190,0x190,-1,203},
+	{0x191,0x191,-1,1},
+	{0x193,0x193,-1,205},
+	{0x194,0x194,-1,207},
+	{0x196,0x196,-1,211},
+	{0x197,0x197,-1,209},
+	{0x198,0x198,-1,1},
+	{0x19c,0x19c,-1,211},
+	{0x19d,0x19d,-1,213},
+	{0x19f,0x19f,-1,214},
+	{0x1a0,0x1a4,2,1},
+	{0x1a6,0x1a6,-1,218},
+	{0x1a7,0x1a7,-1,1},
+	{0x1a9,0x1a9,-1,218},
+	{0x1ac,0x1ac,-1,1},
+	{0x1ae,0x1ae,-1,218},
+	{0x1af,0x1af,-1,1},
+	{0x1b1,0x1b2,1,217},
+	{0x1b3,0x1b5,2,1},
+	{0x1b7,0x1b7,-1,219},
+	{0x1b8,0x1bc,4,1},
+	{0x1c4,0x1c4,-1,2},
+	{0x1c5,0x1c5,-1,1},
+	{0x1c7,0x1c7,-1,2},
+	{0x1c8,0x1c8,-1,1},
+	{0x1ca,0x1ca,-1,2},
+	{0x1cb,0x1db,2,1},
+	{0x1de,0x1ee,2,1},
+	{0x1f1,0x1f1,-1,2},
+	{0x1f2,0x1f4,2,1},
+	{0x1f6,