Generate unicode tables with script when building

3 files changed, 261 insertions, 962 deletions

diff --git a/scripts/genunicodetables.lua b/scripts/genunicodetables.lua
new file mode 100644
index 0000000000..e8de5026de
--- /dev/null
+++ b/scripts/genunicodetables.lua
@@ -0,0 +1,225 @@
+if arg[1] == '--help' then
+  print('Usage:')
+  print('  genunicodetables.lua UnicodeData.txt CaseFolding.txt ' ..
+        'EastAsianWidth.txt')
+  print('                       unicode_tables.generated.h')
+  os.exit(0)
+end
+
+local unicodedata_fname = arg[1]
+local casefolding_fname = arg[2]
+local eastasianwidth_fname = arg[3]
+
+local utf_tables_fname = arg[4]
+
+local split_on_semicolons = function(s)
+  local ret = {}
+  local idx = 1
+  while idx <= #s + 1 do
+    item = s:match('^[^;]*', idx)
+    idx = idx + #item + 1
+    if idx <= #s + 1 then
+      assert(s:sub(idx - 1, idx - 1) == ';')
+    end
+    item = item:gsub('^%s*', '')
+    item = item:gsub('%s*$', '')
+    table.insert(ret, item)
+  end
+  return ret
+end
+
+local fp_lines_to_lists = function(fp, n, has_comments)
+  local ret = {}
+  local line
+  local i = 0
+  while true do
+    i = i + 1
+    line = fp:read('*l')
+    if not line then
+      break
+    end
+    if (not has_comments
+        or (line:sub(1, 1) ~= '#' and not line:match('^%s*$'))) then
+      local l = split_on_semicolons(line)
+      if #l ~= n then
+        io.stderr:write(('Found %s items in line %u, expected %u\n'):format(
+          #l, i, n))
+        io.stderr:write('Line: ' .. line .. '\n')
+        return nil
+      end
+      table.insert(ret, l)
+    end
+  end
+  return ret
+end
+
+local parse_data_to_props = function(ud_fp)
+  return fp_lines_to_lists(ud_fp, 15, false)
+end
+
+local parse_fold_props = function(cf_fp)
+  return fp_lines_to_lists(cf_fp, 4, true)
+end
+
+local parse_width_props = function(eaw_fp)
+  return fp_lines_to_lists(eaw_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(
+      start, end_, step == 0 and -1 or step, add)
+  else
+    return ('  {0x%04x, 0x%04x},\n'):format(start, end_)
+  end
+end
+
+local build_convert_table = function(ut_fp, props, cond_func, nl_index,
+                                     table_name)
+  ut_fp:write('static const convertStruct ' .. table_name .. '[] = {\n')
+  local start = -1
+  local end_ = -1
+  local step = 0
+  local add = -1
+  for _, p in ipairs(props) do
+    if cond_func(p) then
+      local n = tonumber(p[1], 16)
+      local nl = tonumber(p[nl_index], 16)
+      if start >= 0 and add == (nl - n) and (step == 0 or n - end_ == step) then
+        -- Continue with the same range.
+        step = n - end_
+        end_ = n
+      else
+        if start >= 0 then
+          -- Produce previous range.
+          ut_fp:write(make_range(start, end_, step, add))
+        end
+        start = n
+        end_ = n
+        step = 0
+        add = nl - n
+      end
+    end
+  end
+  if start >= 0 then
+    ut_fp:write(make_range(start, end_, step, add))
+  end
+  ut_fp:write('};\n')
+end
+
+local build_case_table = function(ut_fp, dataprops, table_name, index)
+  local cond_func = function(p)
+    return p[index] ~= ''
+  end
+  return build_convert_table(ut_fp, dataprops, cond_func, index,
+                             'to' .. table_name)
+end
+
+local build_fold_table = function(ut_fp, foldprops)
+  local cond_func = function(p)
+    return (p[2] == 'C' or p[2] == 'S')
+  end
+  return build_convert_table(ut_fp, foldprops, cond_func, 3, 'foldCase')
+end
+
+local build_combining_table = function(ut_fp, dataprops)
+  ut_fp:write('static const struct interval combining[] = {\n')
+  local start = -1
+  local end_ = -1
+  for _, p in ipairs(dataprops) do
+    if (({Mn=true, Mc=true, Me=true})[p[3]]) then
+      local n = tonumber(p[1], 16)
+      if start >= 0 and end_ + 1 == n then
+        -- Continue with the same range.
+        end_ = n
+      else
+        if start >= 0 then
+          -- Produce previous range.
+          ut_fp:write(make_range(start, end_))
+        end
+        start = n
+        end_ = n
+      end
+    end
+  end
+  if start >= 0 then
+    ut_fp:write(make_range(start, end_))
+  end
+  ut_fp:write('};\n')
+end
+
+local build_width_table = function(ut_fp, dataprops, widthprops, widths,
+                                   table_name)
+  ut_fp:write('static const struct interval ' .. table_name .. '[] = {\n')
+  local start = -1
+  local end_ = -1
+  local dataidx = 1
+  for _, p in ipairs(widthprops) do
+    if widths[p[2]:sub(1, 1)] then
+      local rng_start, rng_end = p[1]:find('%.%.')
+      local n, n_last
+      if rng_start then
+        -- It is a range. We don’t check for composing char then.
+        n = tonumber(p[1]:sub(1, rng_start - 1), 16)
+        n_last = tonumber(p[1]:sub(rng_end + 1), 16)
+      else
+        n = tonumber(p[1], 16)
+        n_last = n
+      end
+      local dn
+      while true do
+        dn = tonumber(dataprops[dataidx][1], 16)
+        if dn >= n then
+          break
+        end
+        dataidx = dataidx + 1
+      end
+      if dn ~= n and n_last == n then
+        io.stderr:write('Cannot find character ' .. n .. ' in data table.\n')
+      end
+      -- Only use the char when it’s not a composing char.
+      -- But use all chars from a range.
+      local dp = dataprops[dataidx]
+      if (n_last > n) or (not (({Mn=true, Mc=true, Me=true})[dp[3]])) then
+        if start >= 0 and end_ + 1 == n then
+          -- Continue with the same range.
+        else
+          if start >= 0 then
+            ut_fp:write(make_range(start, end_))
+          end
+          start = n
+        end
+        end_ = n_last
+      end
+    end
+  end
+  if start >= 0 then
+    ut_fp:write(make_range(start, 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()
+
+local ut_fp = io.open(utf_tables_fname, 'w')
+
+build_case_table(ut_fp, dataprops, 'Lower', 14)
+build_case_table(ut_fp, dataprops, 'Upper', 13)
+build_combining_table(ut_fp, dataprops)
+
+local cf_fp = io.open(casefolding_fname, 'r')
+local foldprops = parse_fold_props(cf_fp)
+cf_fp:close()
+
+build_fold_table(ut_fp, foldprops)
+
+local eaw_fp = io.open(eastasianwidth_fname, 'r')
+local widthprops = parse_width_props(eaw_fp)
+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')
+
+ut_fp:close()
diff --git a/src/nvim/CMakeLists.txt b/src/nvim/CMakeLists.txt
index d49b8dc416..7348e1475a 100644
--- a/src/nvim/CMakeLists.txt
+++ b/src/nvim/CMakeLists.txt
@@ -27,6 +27,17 @@ set(OPTIONS_GENERATOR ${PROJECT_SOURCE_DIR}/scripts/genoptions.lua)
 set(EVENTS_LIST_FILE ${PROJECT_SOURCE_DIR}/src/nvim/auevents.lua)
 set(EX_CMDS_DEFS_FILE ${PROJECT_SOURCE_DIR}/src/nvim/ex_cmds.lua)
 set(OPTIONS_LIST_FILE ${PROJECT_SOURCE_DIR}/src/nvim/options.lua)
+set(UNICODE_TABLES_GENERATOR ${PROJECT_SOURCE_DIR}/scripts/genunicodetables.lua)
+set(UNICODE_DOWNLOAD_DIR ${PROJECT_BINARY_DIR}/unicode)
+set(DOWNLOAD_URL_BASE "http://unicode.org/Public/UNIDATA")
+set(UNICODEDATA_BASENAME UnicodeData.txt)
+set(CASEFOLDING_BASENAME CaseFolding.txt)
+set(EASTASIANWIDTH_BASENAME EastAsianWidth.txt)
+set(DOWNLOADED_UNICODEDATA ${UNICODE_DOWNLOAD_DIR}/${UNICODEDATA_BASENAME})
+set(DOWNLOADED_CASEFOLDING ${UNICODE_DOWNLOAD_DIR}/${CASEFOLDING_BASENAME})
+set(DOWNLOADED_EASTASIANWIDTH
+    ${UNICODE_DOWNLOAD_DIR}/${EASTASIANWIDTH_BASENAME})
+set(GENERATED_UNICODE_TABLES ${GENERATED_DIR}/unicode_tables.generated.h)
 
 include_directories(${GENERATED_DIR})
 include_directories(${GENERATED_INCLUDES_DIR})
@@ -46,6 +57,8 @@ file(MAKE_DIRECTORY ${GENERATED_INCLUDES_DIR}/msgpack_rpc)
 file(MAKE_DIRECTORY ${GENERATED_INCLUDES_DIR}/tui)
 file(MAKE_DIRECTORY ${GENERATED_INCLUDES_DIR}/event)
 
+file(MAKE_DIRECTORY ${UNICODE_DOWNLOAD_DIR})
+
 file(GLOB NEOVIM_SOURCES *.c os/*.c api/*.c api/private/*.c msgpack_rpc/*.c
   tui/*.c event/*.c)
 file(GLOB_RECURSE NEOVIM_HEADERS *.h)
@@ -143,6 +156,26 @@ foreach(sfile ${NEOVIM_SOURCES}
   endif()
 endforeach()
 
+file(DOWNLOAD ${DOWNLOAD_URL_BASE}/${UNICODEDATA_BASENAME}
+              ${DOWNLOADED_UNICODEDATA})
+file(DOWNLOAD ${DOWNLOAD_URL_BASE}/${CASEFOLDING_BASENAME}
+              ${DOWNLOADED_CASEFOLDING})
+file(DOWNLOAD ${DOWNLOAD_URL_BASE}/${EASTASIANWIDTH_BASENAME}
+              ${DOWNLOADED_EASTASIANWIDTH})
+
+add_custom_command(OUTPUT ${GENERATED_UNICODE_TABLES}
+  COMMAND ${LUA_PRG} ${UNICODE_TABLES_GENERATOR}
+                     ${DOWNLOADED_UNICODEDATA}
+                     ${DOWNLOADED_CASEFOLDING}
+                     ${DOWNLOADED_EASTASIANWIDTH}
+                     ${GENERATED_UNICODE_TABLES}
+  DEPENDS
+    ${UNICODE_TABLES_GENERATOR}
+    ${DOWNLOADED_UNICODEDATA}
+    ${DOWNLOADED_CASEFOLDING}
+    ${DOWNLOADED_EASTASIANWIDTH}
+)
+
 add_custom_command(OUTPUT ${MSGPACK_DISPATCH}
   COMMAND ${LUA_PRG} ${DISPATCH_GENERATOR} ${API_HEADERS} ${MSGPACK_DISPATCH}
   DEPENDS
@@ -159,6 +192,7 @@ list(APPEND NEOVIM_GENERATED_SOURCES
   "${GENERATED_EVENTS_ENUM}"
   "${GENERATED_EVENTS_NAMES_MAP}"
   "${GENERATED_OPTIONS}"
+  "${GENERATED_UNICODE_TABLES}"
 )
 
 add_custom_command(OUTPUT ${GENERATED_EX_CMDS_ENUM} ${GENERATED_EX_CMDS_DEFS}
diff --git a/src/nvim/mbyte.c b/src/nvim/mbyte.c
index 792ec8fd31..100b66a608 100644
--- a/src/nvim/mbyte.c
+++ b/src/nvim/mbyte.c
@@ -115,6 +115,7 @@ struct interval {
 
 #ifdef INCLUDE_GENERATED_DECLARATIONS
 # include "mbyte.c.generated.h"
+# include "unicode_tables.generated.h"
 #endif
 
 /*
@@ -944,225 +945,6 @@ static bool intable(const struct interval *table, size_t n_items, int c)
  */
 int utf_char2cells(int c)
 {
-  /* Sorted list of non-overlapping intervals of East Asian double width
-   * characters, generated with ../runtime/tools/unicode.vim. */
-  static struct interval doublewidth[] =
-  {
-    {0x1100, 0x115f},
-    {0x2329, 0x232a},
-    {0x2e80, 0x2e99},
-    {0x2e9b, 0x2ef3},
-    {0x2f00, 0x2fd5},
-    {0x2ff0, 0x2ffb},
-    {0x3000, 0x303e},
-    {0x3041, 0x3096},
-    {0x3099, 0x30ff},
-    {0x3105, 0x312d},
-    {0x3131, 0x318e},
-    {0x3190, 0x31ba},
-    {0x31c0, 0x31e3},
-    {0x31f0, 0x321e},
-    {0x3220, 0x3247},
-    {0x3250, 0x32fe},
-    {0x3300, 0x4dbf},
-    {0x4e00, 0xa48c},
-    {0xa490, 0xa4c6},
-    {0xa960, 0xa97c},
-    {0xac00, 0xd7a3},
-    {0xf900, 0xfaff},
-    {0xfe10, 0xfe19},
-    {0xfe30, 0xfe52},
-    {0xfe54, 0xfe66},
-    {0xfe68, 0xfe6b},
-    {0xff01, 0xff60},
-    {0xffe0, 0xffe6},
-    {0x1b000, 0x1b001},
-    {0x1f200, 0x1f202},
-    {0x1f210, 0x1f23a},
-    {0x1f240, 0x1f248},
-    {0x1f250, 0x1f251},
-    {0x20000, 0x2fffd},
-    {0x30000, 0x3fffd}
-  };
-  /* 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},
-    {0x0300, 0x036f},
-    {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},
-    {0xfe00, 0xfe0f},
-    {0xfffd, 0xfffd},
-    {0x1f100, 0x1f10a},
-    {0x1f110, 0x1f12d},
-    {0x1f130, 0x1f169},
-    {0x1f170, 0x1f19a},
-    {0xe0100, 0xe01ef},
-    {0xf0000, 0xffffd},
-    {0x100000, 0x10fffd}
-  };
-
   if (c >= 0x100) {
 #ifdef USE_WCHAR_FUNCTIONS
     /*
@@ -1806,241 +1588,6 @@ int utf_char2bytes(int c, char_u *buf)
  */
 bool utf_iscomposing(int c)
 {
-  /* Sorted list of non-overlapping intervals.
-   * Generated by ../runtime/tools/unicode.vim. */
-  static struct interval combining[] =
-  {
-    {0x0300, 0x036f},
-    {0x0483, 0x0489},
-    {0x0591, 0x05bd},
-    {0x05bf, 0x05bf},
-    {0x05c1, 0x05c2},
-    {0x05c4, 0x05c5},
-    {0x05c7, 0x05c7},
-    {0x0610, 0x061a},
-    {0x064b, 0x065f},
-    {0x0670, 0x0670},
-    {0x06d6, 0x06dc},
-    {0x06df, 0x06e4},
-    {0x06e7, 0x06e8},
-    {0x06ea, 0x06ed},
-    {0x0711, 0x0711},
-    {0x0730, 0x074a},
-    {0x07a6, 0x07b0},
-    {0x07eb, 0x07f3},
-    {0x0816, 0x0819},
-    {0x081b, 0x0823},
-    {0x0825, 0x0827},
-    {0x0829, 0x082d},
-    {0x0859, 0x085b},
-    {0x08e4, 0x0903},
-    {0x093a, 0x093c},
-    {0x093e, 0x094f},
-    {0x0951, 0x0957},
-    {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},
-    {0x0c00, 0x0c03},
-    {0x0c3e, 0x0c44},
-    {0x0c46, 0x0c48},
-    {0x0c4a, 0x0c4d},
-    {0x0c55, 0x0c56},
-    {0x0c62, 0x0c63},
-    {0x0c81, 0x0c83},
-    {0x0cbc, 0x0cbc},
-    {0x0cbe, 0x0cc4},
-    {0x0cc6, 0x0cc8},
-    {0x0cca, 0x0ccd},
-    {0x0cd5, 0x0cd6},
-    {0x0ce2, 0x0ce3},
-    {0x0d01, 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},
-    {0x0f8d, 0x0f97},
-    {0x0f99, 0x0fbc},
-    {0x0fc6, 0x0fc6},
-    {0x102b, 0x103e},
-    {0x1056, 0x1059},
-    {0x105e, 0x1060},
-    {0x1062, 0x1064},
-    {0x1067, 0x106d},
-    {0x1071, 0x1074},
-    {0x1082, 0x108d},
-    {0x108f, 0x108f},
-    {0x109a, 0x109d},
-    {0x135d, 0x135f},
-    {0x1712, 0x1714},
-    {0x1732, 0x1734},
-    {0x1752, 0x1753},
-    {0x1772, 0x1773},
-    {0x17b4, 0x17d3},
-    {0x17dd, 0x17dd},
-    {0x180b, 0x180d},
-    {0x18a9, 0x18a9},
-    {0x1920, 0x192b},
-    {0x1930, 0x193b},
-    {0x19b0, 0x19c0},
-    {0x19c8, 0x19c9},
-    {0x1a17, 0x1a1b},
-    {0x1a55, 0x1a5e},
-    {0x1a60, 0x1a7c},
-    {0x1a7f, 0x1a7f},
-    {0x1ab0, 0x1abe},
-    {0x1b00, 0x1b04},
-    {0x1b34, 0x1b44},
-    {0x1b6b, 0x1b73},
-    {0x1b80, 0x1b82},
-    {0x1ba1, 0x1bad},
-    {0x1be6, 0x1bf3},
-    {0x1c24, 0x1c37},
-    {0x1cd0, 0x1cd2},
-    {0x1cd4, 0x1ce8},
-    {0x1ced, 0x1ced},
-    {0x1cf2, 0x1cf4},
-    {0x1cf8, 0x1cf9},
-    {0x1dc0, 0x1df5},
-    {0x1dfc, 0x1dff},
-    {0x20d0, 0x20f0},
-    {0x2cef, 0x2cf1},
-    {0x2d7f, 0x2d7f},
-    {0x2de0, 0x2dff},
-    {0x302a, 0x302f},
-    {0x3099, 0x309a},
-    {0xa66f, 0xa672},
-    {0xa674, 0xa67d},
-    {0xa69f, 0xa69f},
-    {0xa6f0, 0xa6f1},
-    {0xa802, 0xa802},
-    {0xa806, 0xa806},
-    {0xa80b, 0xa80b},
-    {0xa823, 0xa827},
-    {0xa880, 0xa881},
-    {0xa8b4, 0xa8c4},
-    {0xa8e0, 0xa8f1},
-    {0xa926, 0xa92d},
-    {0xa947, 0xa953},
-    {0xa980, 0xa983},
-    {0xa9b3, 0xa9c0},
-    {0xa9e5, 0xa9e5},
-    {0xaa29, 0xaa36},
-    {0xaa43, 0xaa43},
-    {0xaa4c, 0xaa4d},
-    {0xaa7b, 0xaa7d},
-    {0xaab0, 0xaab0},
-    {0xaab2, 0xaab4},
-    {0xaab7, 0xaab8},
-    {0xaabe, 0xaabf},
-    {0xaac1, 0xaac1},
-    {0xaaeb, 0xaaef},
-    {0xaaf5, 0xaaf6},
-    {0xabe3, 0xabea},
-    {0xabec, 0xabed},
-    {0xfb1e, 0xfb1e},
-    {0xfe00, 0xfe0f},
-    {0xfe20, 0xfe2d},
-    {0x101fd, 0x101fd},
-    {0x102e0, 0x102e0},
-    {0x10376, 0x1037a},
-    {0x10a01, 0x10a03},
-    {0x10a05, 0x10a06},
-    {0x10a0c, 0x10a0f},
-    {0x10a38, 0x10a3a},
-    {0x10a3f, 0x10a3f},
-    {0x10ae5, 0x10ae6},
-    {0x11000, 0x11002},
-    {0x11038, 0x11046},
-    {0x1107f, 0x11082},
-    {0x110b0, 0x110ba},
-    {0x11100, 0x11102},
-    {0x11127, 0x11134},
-    {0x11173, 0x11173},
-    {0x11180, 0x11182},
-    {0x111b3, 0x111c0},
-    {0x1122c, 0x11237},
-    {0x112df, 0x112ea},
-    {0x11301, 0x11303},
-    {0x1133c, 0x1133c},
-    {0x1133e, 0x11344},
-    {0x11347, 0x11348},
-    {0x1134b, 0x1134d},
-    {0x11357, 0x11357},
-    {0x11362, 0x11363},
-    {0x11366, 0x1136c},
-    {0x11370, 0x11374},
-    {0x114b0, 0x114c3},
-    {0x115af, 0x115b5},
-    {0x115b8, 0x115c0},
-    {0x11630, 0x11640},
-    {0x116ab, 0x116b7},
-    {0x16af0, 0x16af4},
-    {0x16b30, 0x16b36},
-    {0x16f51, 0x16f7e},
-    {0x16f8f, 0x16f92},
-    {0x1bc9d, 0x1bc9e},
-    {0x1d165, 0x1d169},
-    {0x1d16d, 0x1d172},
-    {0x1d17b, 0x1d182},
-    {0x1d185, 0x1d18b},
-    {0x1d1aa, 0x1d1ad},
-    {0x1d242, 0x1d244},
-    {0x1e8d0, 0x1e8d6},
-    {0xe0100, 0xe01ef}
-  };
-
   return intable(combining, ARRAY_SIZE(combining), c);
 }
 
@@ -2188,192 +1735,11 @@ int utf_class(int c)
  */
 
 /*
- * 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.
- */
-
-static convertStruct foldCase[] =
-{
-  {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},
-  {0x37f,0x37f,-1,116},
-  {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},
-  {0x4d0,0x52e,2,1},
-  {0x531,0x556,1,48},
-  {0x10a0,0x10c5,1,7264},
-  {0x10c7,0x10cd,6,7264},
-  {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},
-  {0x2cf2,0xa640,31054,1},
-  {0xa642,0xa66c,2,1},
-  {0xa680,0xa69a,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},
-  {0xa78d,0xa78d,-1,-42280},
-  {0xa790,0xa792,2,1},
-  {0xa796,0xa7a8,2,1},
-  {0xa7aa,0xa7aa,-1,-42308},
-  {0xa7ab,0xa7ab,-1,-42319},
-  {0xa7ac,0xa7ac,-1,-42315},
-  {0xa7ad,0xa7ad,-1,-42305},
-  {0xa7b0,0xa7b0,-1,-42258},
-  {0xa7b1,0xa7b1,-1,-42282},
-  {0xff21,0xff3a,1,32},
-  {0x10400,0x10427,1,40},
-  {0x118a0,0x118bf,1,32}
-};
-
-
-/*
  * Generic conversion function for case operations.
  * Return the converted equivalent of "a", which is a UCS-4 character.  Use
  * the given conversion "table".  Uses binary search on "table".
  */
-static int utf_convert(int a, convertStruct *table, size_t n_items)
+static int utf_convert(int a, const convertStruct *const table, size_t n_items)
 {
   size_t start, mid, end;   /* indices into table */
 
@@ -2405,332 +1771,6 @@ int utf_fold(int a)
   return utf_convert(a, foldCase, ARRAY_SIZE(foldCase));
 }
 
-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},
-  {0x1c4,0x1c4,-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},
-  {0x370,0x372,2,1},
-  {0x376,0x376,-1,1},
-  {0x37f,0x37f,-1,116},
-  {0x386,0x386,-1,38},
-  {0x388,0x38a,1,37},
-  {0x38c,0x38c,-1,64},
-  {0x38e,0x38f,1,63},
-  {0x391,0x3a1,1,32},
-  {0x3a3,0x3ab,1,32},
-  {0x3cf,0x3cf,-1,8},
-  {0x3d8,0x3ee,2,1},
-  {0x3f4,0x3f4,-1,-60},
-  {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},
-  {0x4d0,0x52e,2,1},
-  {0x531,0x556,1,48},
-  {0x10a0,0x10c5,1,7264},
-  {0x10c7,0x10cd,6,7264},
-  {0x1e00,0x1e94,2,1},
-  {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},
-  {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},
-  {0x2cf2,0xa640,31054,1},
-  {0xa642,0xa66c,2,1},
-  {0xa680,0xa69a,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},
-  {0xa78d,0xa78d,-1,-42280},
-  {0xa790,0xa792,2,1},
-  {0xa796,0xa7a8,2,1},
-  {0xa7aa,0xa7aa,-1,-42308},
-  {0xa7ab,0xa7ab,-1,-42319},
-  {0xa7ac,0xa7ac,-1,-42315},
-  {0xa7ad,0xa7ad,-1,-42305},
-  {0xa7b0,0xa7b0,-1,-42258},
-  {0xa7b1,0xa7b1,-1,-42282},
-  {0xff21,0xff3a,1,32},
-  {0x10400,0x10427,1,40},
-  {0x118a0,0x118bf,1,32}
-};
-
-static convertStruct toUpper[] =
-{
-  {0x61,0x7a,1,-32},
-  {0xb5,0xb5,-1,743},
-  {0xe0,0xf6,1,-32},
-  {0xf8,0xfe,1,-32},
-  {0xff,0xff,-1,121},
-  {0x101,0x12f,2,-1},
-  {0x131,0x131,-1,-232},
-  {0x133,0x137,2,-1},
-  {0x13a,0x148,2,-1},
-  {0x14b,0x177,2,-1},
-  {0x17a,0x17e,2,-1},
-  {0x17f,0x17f,-1,-300},
-  {0x180,0x180,-1,195},
-  {0x183,0x185,2,-1},
-  {0x188,0x18c,4,-1},
-  {0x192,0x192,-1,-1},
-  {0x195,0x195,-1,97},
-  {0x199,0x199,-1,-1},
-  {0x19a,0x19a,-1,163},
-  {0x19e,0x19e,-1,130},
-  {0x1a1,0x1a5,2,-1},
-  {0x1a8,0x1ad,5,-1},
-  {0x1b0,0x1b4,4,-1},
-  {0x1b6,0x1b9,3,-1},
-  {0x1bd,0x1bd,-1,-1},
-  {0x1bf,0x1bf,-1,56},
-  {0x1c5,0x1c5,-1,-1},
-  {0x1c6,0x1c6,-1,-2},
-  {0x1c8,0x1c8,-1,-1},
-  {0x1c9,0x1c9,-1,-2},
-  {0x1cb,0x1cb,-1,-1},
-  {0x1cc,0x1cc,-1,-2},
-  {0x1ce,0x1dc,2,-1},
-  {0x1dd,0x1dd,-1,-79},
-  {0x1df,0x1ef,2,-1},
-  {0x1f2,0x1f2,-1,-1},
-  {0x1f3,0x1f3,-1,-2},
-  {0x1f5,0x1f9,4,-1},
-  {0x1fb,0x21f,2,-1},
-  {0x223,0x233,2,-1},
-  {0x23c,0x23c,-1,-1},
-  {0x23f,0x240,1,10815},
-  {0x242,0x247,5,-1},
-  {0x249,0x24f,2,-1},
-  {0x250,0x250,-1,10783},
-  {0x251,0x251,-1,10780},
-  {0x252,0x252,-1,10782},
-  {0x253,0x253,-1,-210},
-  {0x254,0x254,-1,-206},
-  {0x256,0x257,1,-205},
-  {0x259,0x259,-1,-202},
-  {0x25b,0x25b,-1,-203},
-  {0x25c,0x25c,-1,42319},
-  {0x260,0x260,-1,-205},
-  {0x261,0x261,-1,42315},
-  {0x263,0x263,-1,-207},
-  {0x265,0x265,-1,42280},
-  {0x266,0x266,-1,42308},
-  {0x268,0x268,-1,-209},
-  {0x269,0x269,-1,-211},
-  {0x26b,0x26b,-1,10743},
-  {0x26c,0x26c,-1,42305},
-  {0x26f,0x26f,-1,-211},
-  {0x271,0x271,-1,10749},
-  {0x272,0x272,-1,-213},
-  {0x275,0x275,-1,-214},
-  {0x27d,0x27d,-1,10727},
-  {0x280,0x283,3,-218},
-  {0x287,0x287,-1,42282},
-  {0x288,0x288,-1,-218},
-  {0x289,0x289,-1,-69},
-  {0x28a,0x28b,1,-217},
-  {0x28c,0x28c,-1,-71},
-  {0x292,0x292,-1,-219},
-  {0x29e,0x29e,-1,42258},
-  {0x345,0x345,-1,84},
-  {0x371,0x373,2,-1},
-  {0x377,0x377,-1,-1},
-  {0x37b,0x37d,1,130},
-  {0x3ac,0x3ac,-1,-38},
-  {0x3ad,0x3af,1,-37},
-  {0x3b1,0x3c1,1,-32},
-  {0x3c2,0x3c2,-1,-31},
-  {0x3c3,0x3cb,1,-32},
-  {0x3cc,0x3cc,-1,-64},
-  {0x3cd,0x3ce,1,-63},
-  {0x3d0,0x3d0,-1,-62},
-  {0x3d1,0x3d1,-1,-57},
-  {0x3d5,0x3d5,-1,-47},
-  {0x3d6,0x3d6,-1,-54},
-  {0x3d7,0x3d7,-1,-8},
-  {0x3d9,0x3ef,2,-1},
-  {0x3f0,0x3f0,-1,-86},
-  {0x3f1,0x3f1,-1,-80},
-  {0x3f2,0x3f2,-1,7},
-  {0x3f3,0x3f3,-1,-116},
-  {0x3f5,0x3f5,-1,-96},
-  {0x3f8,0x3fb,3,-1},
-  {0x430,0x44f,1,-32},
-  {0x450,0x45f,1,-80},
-  {0x461,0x481,2,-1},
-  {0x48b,0x4bf,2,-1},
-  {0x4c2,0x4ce,2,-1},
-  {0x4cf,0x4cf,-1,-15},
-  {0x4d1,0x52f,2,-1},
-  {0x561,0x586,1,-48},
-  {0x1d79,0x1d79,-1,35332},
-  {0x1d7d,0x1d7d,-1,3814},
-  {0x1e01,0x1e95,2,-1},
-  {0x1e9b,0x1e9b,-1,-59},
-  {0x1ea1,0x1eff,2,-1},
-  {0x1f00,0x1f07,1,8},
-  {0x1f10,0x1f15,1,8},
-  {0x1f20,0x1f27,1,8},
-  {0x1f30,0x1f37,1,8},
-  {0x1f40,0x1f45,1,8},
-  {0x1f51,0x1f57,2,8},
-  {0x1f60,0x1f67,1,8},
-  {0x1f70,0x1f71,1,74},
-  {0x1f72,0x1f75,1,86},
-  {0x1f76,0x1f77,1,100},
-  {0x1f78,0x1f79,1,128},
-  {0x1f7a,0x1f7b,1,112},
-  {0x1f7c,0x1f7d,1,126},
-  {0x1f80,0x1f87,1,8},
-  {0x1f90,0x1f97,1,8},
-  {0x1fa0,0x1fa7,1,8},
-  {0x1fb0,0x1fb1,1,8},
-  {0x1fb3,0x1fb3,-1,9},
-  {0x1fbe,0x1fbe,-1,-7205},
-  {0x1fc3,0x1fc3,-1,9},
-  {0x1fd0,0x1fd1,1,8},
-  {0x1fe0,0x1fe1,1,8},
-  {0x1fe5,0x1fe5,-1,7},
-  {0x1ff3,0x1ff3,-1,9},
-  {0x214e,0x214e,-1,-28},
-  {0x2170,0x217f,1,-16},
-  {0x2184,0x2184,-1,-1},
-  {0x24d0,0x24e9,1,-26},
-  {0x2c30,0x2c5e,1,-48},
-  {0x2c61,0x2c61,-1,-1},
-  {0x2c65,0x2c65,-1,-10795},
-  {0x2c66,0x2c66,-1,-10792},
-  {0x2c68,0x2c6c,2,-1},
-  {0x2c73,0x2c76,3,-1},
-  {0x2c81,0x2ce3,2,-1},
-  {0x2cec,0x2cee,2,-1},
-  {0x2cf3,0x2cf3,-1,-1},
-  {0x2d00,0x2d25,1,-7264},
-  {0x2d27,0x2d2d,6,-7264},
-  {0xa641,0xa66d,2,-1},
-  {0xa681,0xa69b,2,-1},
-  {0xa723,0xa72f,2,-1},
-  {0xa733,0xa76f,2,-1},
-  {0xa77a,0xa77c,2,-1},
-  {0xa77f,0xa787,2,-1},
-  {0xa78c,0xa791,5,-1},
-  {0xa793,0xa797,4,-1},
-  {0xa799,0xa7a9,2,-1},
-  {0xff41,0xff5a,1,-32},
-  {0x10428,0x1044f,1,-40},
-  {0x118c0,0x118df,1,-32}
-};
-
 /*
  * Return the upper-case equivalent of "a", which is a UCS-4 character.  Use
  * simple case folding.