Improve unicode property abbreviation support (#74)

* Improve unicode property abbreviation support

* Auto-generate script names

Co-authored-by: Zoltan Herczeg <hzmester@freemail.hu>

maint/GenerateCommon.py

@@ -13,90 +13,6 @@
 #                             DATA LISTS
 # ---------------------------------------------------------------------------
 
-# The lists of script names and script abbreviations must be kept in step. Note
-# that the pcre2pattern and pcre2syntax documentation has lists of scripts.
-
-script_names = ['Unknown', 'Arabic', 'Armenian', 'Bengali', 'Bopomofo', 'Braille', 'Buginese', 'Buhid', 'Canadian_Aboriginal', \
- 'Cherokee', 'Common', 'Coptic', 'Cypriot', 'Cyrillic', 'Deseret', 'Devanagari', 'Ethiopic', 'Georgian', \
- 'Glagolitic', 'Gothic', 'Greek', 'Gujarati', 'Gurmukhi', 'Han', 'Hangul', 'Hanunoo', 'Hebrew', 'Hiragana', \
- 'Inherited', 'Kannada', 'Katakana', 'Kharoshthi', 'Khmer', 'Lao', 'Latin', 'Limbu', 'Linear_B', 'Malayalam', \
- 'Mongolian', 'Myanmar', 'New_Tai_Lue', 'Ogham', 'Old_Italic', 'Old_Persian', 'Oriya', 'Osmanya', 'Runic', \
- 'Shavian', 'Sinhala', 'Syloti_Nagri', 'Syriac', 'Tagalog', 'Tagbanwa', 'Tai_Le', 'Tamil', 'Telugu', 'Thaana', \
- 'Thai', 'Tibetan', 'Tifinagh', 'Ugaritic', 'Yi', \
- # New for Unicode 5.0
- 'Balinese', 'Cuneiform', 'Nko', 'Phags_Pa', 'Phoenician', \
- # New for Unicode 5.1
- 'Carian', 'Cham', 'Kayah_Li', 'Lepcha', 'Lycian', 'Lydian', 'Ol_Chiki', 'Rejang', 'Saurashtra', 'Sundanese', 'Vai', \
- # New for Unicode 5.2
- 'Avestan', 'Bamum', 'Egyptian_Hieroglyphs', 'Imperial_Aramaic', \
- 'Inscriptional_Pahlavi', 'Inscriptional_Parthian', \
- 'Javanese', 'Kaithi', 'Lisu', 'Meetei_Mayek', \
- 'Old_South_Arabian', 'Old_Turkic', 'Samaritan', 'Tai_Tham', 'Tai_Viet', \
- # New for Unicode 6.0.0
- 'Batak', 'Brahmi', 'Mandaic', \
-# New for Unicode 6.1.0
- 'Chakma', 'Meroitic_Cursive', 'Meroitic_Hieroglyphs', 'Miao', 'Sharada', 'Sora_Sompeng', 'Takri',
-# New for Unicode 7.0.0
- 'Bassa_Vah', 'Caucasian_Albanian', 'Duployan', 'Elbasan', 'Grantha', 'Khojki', 'Khudawadi',
- 'Linear_A', 'Mahajani', 'Manichaean', 'Mende_Kikakui', 'Modi', 'Mro', 'Nabataean',
- 'Old_North_Arabian', 'Old_Permic', 'Pahawh_Hmong', 'Palmyrene', 'Psalter_Pahlavi',
- 'Pau_Cin_Hau', 'Siddham', 'Tirhuta', 'Warang_Citi',
-# New for Unicode 8.0.0
- 'Ahom', 'Anatolian_Hieroglyphs', 'Hatran', 'Multani', 'Old_Hungarian',
- 'SignWriting',
-# New for Unicode 10.0.0
- 'Adlam', 'Bhaiksuki', 'Marchen', 'Newa', 'Osage', 'Tangut', 'Masaram_Gondi',
- 'Nushu', 'Soyombo', 'Zanabazar_Square',
-# New for Unicode 11.0.0
-  'Dogra', 'Gunjala_Gondi', 'Hanifi_Rohingya', 'Makasar', 'Medefaidrin',
-  'Old_Sogdian', 'Sogdian',
-# New for Unicode 12.0.0
-  'Elymaic', 'Nandinagari', 'Nyiakeng_Puachue_Hmong', 'Wancho',
-# New for Unicode 13.0.0
-  'Chorasmian', 'Dives_Akuru', 'Khitan_Small_Script', 'Yezidi',
-# New for Unicode 14.0.0
-  'Cypro_Minoan', 'Old_Uyghur', 'Tangsa', 'Toto', 'Vithkuqi'
- ]
-
-script_abbrevs = [
-  'Zzzz', 'Arab', 'Armn', 'Beng', 'Bopo', 'Brai', 'Bugi', 'Buhd', 'Cans',
-  'Cher', 'Zyyy', 'Copt', 'Cprt', 'Cyrl', 'Dsrt', 'Deva', 'Ethi', 'Geor',
-  'Glag', 'Goth', 'Grek', 'Gujr', 'Guru', 'Hani', 'Hang', 'Hano', 'Hebr',
-  'Hira', 'Zinh', 'Knda', 'Kana', 'Khar', 'Khmr', 'Laoo', 'Latn', 'Limb',
-  'Linb', 'Mlym', 'Mong', 'Mymr', 'Talu', 'Ogam', 'Ital', 'Xpeo', 'Orya',
-  'Osma', 'Runr', 'Shaw', 'Sinh', 'Sylo', 'Syrc', 'Tglg', 'Tagb', 'Tale',
-  'Taml', 'Telu', 'Thaa', 'Thai', 'Tibt', 'Tfng', 'Ugar', 'Yiii',
-#New for Unicode 5.0
-  'Bali', 'Xsux', 'Nkoo', 'Phag', 'Phnx',
-#New for Unicode 5.1
-  'Cari', 'Cham', 'Kali', 'Lepc', 'Lyci', 'Lydi', 'Olck', 'Rjng', 'Saur',
-  'Sund', 'Vaii',
-#New for Unicode 5.2
-  'Avst', 'Bamu', 'Egyp', 'Armi', 'Phli', 'Prti', 'Java', 'Kthi', 'Lisu',
-  'Mtei', 'Sarb', 'Orkh', 'Samr', 'Lana', 'Tavt',
-#New for Unicode 6.0.0
-  'Batk', 'Brah', 'Mand',
-#New for Unicode 6.1.0
-  'Cakm', 'Merc', 'Mero', 'Plrd', 'Shrd', 'Sora', 'Takr',
-#New for Unicode 7.0.0
-  'Bass', 'Aghb', 'Dupl', 'Elba', 'Gran', 'Khoj', 'Sind', 'Lina', 'Mahj',
-  'Mani', 'Mend', 'Modi', 'Mroo', 'Nbat', 'Narb', 'Perm', 'Hmng', 'Palm',
-  'Phlp', 'Pauc', 'Sidd', 'Tirh', 'Wara',
-#New for Unicode 8.0.0
-  'Ahom', 'Hluw', 'Hatr', 'Mult', 'Hung', 'Sgnw',
-#New for Unicode 10.0.0
-  'Adlm', 'Bhks', 'Marc', 'Newa', 'Osge', 'Tang', 'Gonm', 'Nshu', 'Soyo',
-  'Zanb',
-#New for Unicode 11.0.0
-  'Dogr', 'Gong', 'Rohg', 'Maka', 'Medf', 'Sogo', 'Sogd',
-#New for Unicode 12.0.0
-  'Elym', 'Nand', 'Hmnp', 'Wcho',
-#New for Unicode 13.0.0
-  'Chrs', 'Diak', 'Kits', 'Yezi',
-#New for Unicode 14.0.0
-  'Cpmn', 'Ougr', 'Tngs', 'Toto', 'Vith'
- ]
-
 # BIDI classes in the DerivedBidiClass.txt file, with comments.
 
 bidi_classes = [
@@ -185,14 +101,66 @@ break_properties = [
   ]
 
 # ---------------------------------------------------------------------------
-#                      REORDERING SCRIPT NAMES
+#                     COLLECTING PROPERTY NAMES
 # ---------------------------------------------------------------------------
 
 import re
 
+script_names = ['Unknown']
+abbreviations = {}
+
+def collect_property_names():
+  global script_names
+  global abbreviations
+
+  names_re = re.compile(r'^[0-9A-F]{4,6}(?:\.\.[0-9A-F]{4,6})? +; ([A-Za-z_]+) #')
+
+  last_script_name = ""
+  with open("Unicode.tables/Scripts.txt") as f:
+    for line in f:
+      match_obj = names_re.match(line)
+
+      if match_obj == None or match_obj.group(1) == last_script_name:
+        continue
+
+      last_script_name = match_obj.group(1)
+      script_names.append(last_script_name)
+
+  # Sometimes there is comment in the line
+  # so splitting around semicolon is not enough
+  value_alias_re = re.compile(r' *([A-Za-z_]+) *; *([A-Za-z_]+) *; *([A-Za-z_]+)(?: *; *([A-Za-z_ ]+))?')
+
+  with open("Unicode.tables/PropertyValueAliases.txt") as f:
+    for line in f:
+      match_obj = value_alias_re.match(line)
+
+      if match_obj == None:
+        continue
+
+      if match_obj.group(1) == "sc":
+        if match_obj.group(2) == match_obj.group(3):
+          abbreviations[match_obj.group(3)] = ()
+        elif match_obj.group(4) == None:
+          abbreviations[match_obj.group(3)] = (match_obj.group(2),)
+        else:
+          abbreviations[match_obj.group(3)] = (match_obj.group(2), match_obj.group(4))
+
+collect_property_names()
+
+# ---------------------------------------------------------------------------
+#                      REORDERING SCRIPT NAMES
+# ---------------------------------------------------------------------------
+
+script_abbrevs = []
+
 def reorder_scripts():
   global script_names
   global script_abbrevs
+  global abbreviations
+
+  for name in script_names:
+    abbrevs = abbreviations[name]
+    script_abbrevs.append(name if len(abbrevs) == 0 else abbrevs[0])
 
   extended_script_abbrevs = set()
   with open("Unicode.tables/ScriptExtensions.txt") as f:

maint/GenerateUcpTables.py

@@ -48,10 +48,10 @@
 # Import common data lists and functions
 
 from GenerateCommon import \
+  abbreviations, \
   bidi_classes, \
   category_names, \
   general_category_names, \
-  script_abbrevs, \
   script_names, \
   open_output
 
@@ -75,14 +75,15 @@ category_names = category_names[::2]
 # Create standardized versions of the names by lowercasing and removing
 # underscores.
 
+def stdname(x):
+  return x.lower().replace('_', '')
+
 def stdnames(x):
   y = [''] * len(x)
   for i in range(len(x)):
-    y[i] = x[i].lower().replace('_', '')
+    y[i] = stdname(x[i])
   return y
 
-std_script_names = stdnames(script_names)
-std_script_abbrevs = stdnames(script_abbrevs)
 std_category_names = stdnames(category_names)
 std_general_category_names = stdnames(general_category_names)
 std_bidi_class_names = stdnames(bidi_class_names)
@@ -92,18 +93,16 @@ std_bidi_class_names = stdnames(bidi_class_names)
 # latter is used for the ucp_xx names. NOTE: for the script abbreviations, we
 # still use the full original names.
 
+utt_table = []
+
 scx_end = script_names.index('Unknown')
 
-utt_table  = list(zip(std_script_names[0:scx_end], script_names[0:scx_end], ['PT_SCX'] * scx_end))
+for idx, name in enumerate(script_names):
-utt_table += list(zip(std_script_names[scx_end:], script_names[scx_end:], ['PT_SC'] * (len(script_names) - scx_end)))
+  pt_type = 'PT_SCX' if idx < scx_end else 'PT_SC'
-utt_table += list(zip(std_script_abbrevs[0:scx_end], script_names[0:scx_end], ['PT_SCX'] * scx_end))
-utt_table += list(zip(std_script_abbrevs[scx_end:], script_names[scx_end:], ['PT_SC'] * (len(script_names) - scx_end)))
 
-# At lease one script abbreviation is the same as the full name of the script,
+  utt_table.append((stdname(name), name, pt_type))
-# so we must remove duplicates. It doesn't matter if this operation changes the
+  for abbrev in abbreviations[name]:
-# order, because we are going to sort the list later.
+    utt_table.append((stdname(abbrev), name, pt_type))
-
-utt_table = list(set(utt_table))
 
 # Add the remaining property lists
 

src/pcre2_ucp.h

@@ -153,45 +153,45 @@ enum {
 
 enum {
   /* Scripts which has characters in other scripts. */
-  ucp_Arabic,
-  ucp_Bengali,
-  ucp_Bopomofo,
-  ucp_Buginese,
-  ucp_Buhid,
-  ucp_Coptic,
-  ucp_Cypriot,
-  ucp_Cyrillic,
-  ucp_Devanagari,
-  ucp_Georgian,
-  ucp_Glagolitic,
-  ucp_Greek,
-  ucp_Gujarati,
-  ucp_Gurmukhi,
-  ucp_Han,
-  ucp_Hangul,
-  ucp_Hanunoo,
-  ucp_Hiragana,
-  ucp_Kannada,
-  ucp_Katakana,
   ucp_Latin,
-  ucp_Limbu,
+  ucp_Greek,
-  ucp_Linear_B,
+  ucp_Cyrillic,
-  ucp_Malayalam,
+  ucp_Arabic,
-  ucp_Mongolian,
-  ucp_Myanmar,
-  ucp_Oriya,
-  ucp_Sinhala,
-  ucp_Syloti_Nagri,
   ucp_Syriac,
-  ucp_Tagalog,
+  ucp_Thaana,
-  ucp_Tagbanwa,
+  ucp_Devanagari,
-  ucp_Tai_Le,
+  ucp_Bengali,
+  ucp_Gurmukhi,
+  ucp_Gujarati,
+  ucp_Oriya,
   ucp_Tamil,
   ucp_Telugu,
-  ucp_Thaana,
+  ucp_Kannada,
+  ucp_Malayalam,
+  ucp_Sinhala,
+  ucp_Myanmar,
+  ucp_Georgian,
+  ucp_Hangul,
+  ucp_Mongolian,
+  ucp_Hiragana,
+  ucp_Katakana,
+  ucp_Bopomofo,
+  ucp_Han,
   ucp_Yi,
-  ucp_Nko,
+  ucp_Tagalog,
+  ucp_Hanunoo,
+  ucp_Buhid,
+  ucp_Tagbanwa,
+  ucp_Limbu,
+  ucp_Tai_Le,
+  ucp_Linear_B,
+  ucp_Cypriot,
+  ucp_Buginese,
+  ucp_Coptic,
+  ucp_Glagolitic,
+  ucp_Syloti_Nagri,
   ucp_Phags_Pa,
+  ucp_Nko,
   ucp_Kayah_Li,
   ucp_Javanese,
   ucp_Kaithi,
@@ -202,13 +202,13 @@ enum {
   ucp_Duployan,
   ucp_Grantha,
   ucp_Khojki,
-  ucp_Khudawadi,
   ucp_Linear_A,
   ucp_Mahajani,
   ucp_Manichaean,
   ucp_Modi,
   ucp_Old_Permic,
   ucp_Psalter_Pahlavi,
+  ucp_Khudawadi,
   ucp_Tirhuta,
   ucp_Multani,
   ucp_Adlam,
@@ -224,70 +224,70 @@ enum {
 
   /* Scripts which has no characters in other scripts. */
   ucp_Unknown,
-  ucp_Armenian,
-  ucp_Braille,
-  ucp_Canadian_Aboriginal,
-  ucp_Cherokee,
   ucp_Common,
-  ucp_Deseret,
+  ucp_Armenian,
-  ucp_Ethiopic,
-  ucp_Gothic,
   ucp_Hebrew,
-  ucp_Inherited,
-  ucp_Kharoshthi,
-  ucp_Khmer,
-  ucp_Lao,
-  ucp_New_Tai_Lue,
-  ucp_Ogham,
-  ucp_Old_Italic,
-  ucp_Old_Persian,
-  ucp_Osmanya,
-  ucp_Runic,
-  ucp_Shavian,
   ucp_Thai,
+  ucp_Lao,
   ucp_Tibetan,
-  ucp_Tifinagh,
+  ucp_Ethiopic,
+  ucp_Cherokee,
+  ucp_Canadian_Aboriginal,
+  ucp_Ogham,
+  ucp_Runic,
+  ucp_Khmer,
+  ucp_Old_Italic,
+  ucp_Gothic,
+  ucp_Deseret,
+  ucp_Inherited,
   ucp_Ugaritic,
+  ucp_Shavian,
+  ucp_Osmanya,
+  ucp_Braille,
+  ucp_New_Tai_Lue,
+  ucp_Tifinagh,
+  ucp_Old_Persian,
+  ucp_Kharoshthi,
   ucp_Balinese,
   ucp_Cuneiform,
   ucp_Phoenician,
-  ucp_Carian,
-  ucp_Cham,
-  ucp_Lepcha,
-  ucp_Lycian,
-  ucp_Lydian,
-  ucp_Ol_Chiki,
-  ucp_Rejang,
-  ucp_Saurashtra,
   ucp_Sundanese,
+  ucp_Lepcha,
+  ucp_Ol_Chiki,
   ucp_Vai,
-  ucp_Avestan,
+  ucp_Saurashtra,
-  ucp_Bamum,
+  ucp_Rejang,
-  ucp_Egyptian_Hieroglyphs,
+  ucp_Lycian,
-  ucp_Imperial_Aramaic,
+  ucp_Carian,
-  ucp_Inscriptional_Pahlavi,
+  ucp_Lydian,
-  ucp_Inscriptional_Parthian,
+  ucp_Cham,
-  ucp_Lisu,
-  ucp_Meetei_Mayek,
-  ucp_Old_South_Arabian,
-  ucp_Old_Turkic,
-  ucp_Samaritan,
   ucp_Tai_Tham,
   ucp_Tai_Viet,
+  ucp_Avestan,
+  ucp_Egyptian_Hieroglyphs,
+  ucp_Samaritan,
+  ucp_Lisu,
+  ucp_Bamum,
+  ucp_Meetei_Mayek,
+  ucp_Imperial_Aramaic,
+  ucp_Old_South_Arabian,
+  ucp_Inscriptional_Parthian,
+  ucp_Inscriptional_Pahlavi,
+  ucp_Old_Turkic,
   ucp_Batak,
   ucp_Brahmi,
   ucp_Meroitic_Cursive,
   ucp_Meroitic_Hieroglyphs,
   ucp_Miao,
   ucp_Sora_Sompeng,
-  ucp_Bassa_Vah,
   ucp_Caucasian_Albanian,
+  ucp_Bassa_Vah,
   ucp_Elbasan,
+  ucp_Pahawh_Hmong,
   ucp_Mende_Kikakui,
   ucp_Mro,
-  ucp_Nabataean,
   ucp_Old_North_Arabian,
-  ucp_Pahawh_Hmong,
+  ucp_Nabataean,
   ucp_Palmyrene,
   ucp_Pau_Cin_Hau,
   ucp_Siddham,

src/pcre2_ucptables.c

@@ -340,6 +340,8 @@ the "loose matching" rules that Unicode advises and Perl uses. */
 #define STRING_prti0 STR_p STR_r STR_t STR_i "\0"
 #define STRING_ps0 STR_p STR_s "\0"
 #define STRING_psalterpahlavi0 STR_p STR_s STR_a STR_l STR_t STR_e STR_r STR_p STR_a STR_h STR_l STR_a STR_v STR_i "\0"
+#define STRING_qaac0 STR_q STR_a STR_a STR_c "\0"
+#define STRING_qaai0 STR_q STR_a STR_a STR_i "\0"
 #define STRING_rejang0 STR_r STR_e STR_j STR_a STR_n STR_g "\0"
 #define STRING_rjng0 STR_r STR_j STR_n STR_g "\0"
 #define STRING_rohg0 STR_r STR_o STR_h STR_g "\0"
@@ -407,7 +409,7 @@ the "loose matching" rules that Unicode advises and Perl uses. */
 #define STRING_tifinagh0 STR_t STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0"
 #define STRING_tirh0 STR_t STR_i STR_r STR_h "\0"
 #define STRING_tirhuta0 STR_t STR_i STR_r STR_h STR_u STR_t STR_a "\0"
-#define STRING_tngs0 STR_t STR_n STR_g STR_s "\0"
+#define STRING_tnsa0 STR_t STR_n STR_s STR_a "\0"
 #define STRING_toto0 STR_t STR_o STR_t STR_o "\0"
 #define STRING_ugar0 STR_u STR_g STR_a STR_r "\0"
 #define STRING_ugaritic0 STR_u STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0"
@@ -729,6 +731,8 @@ const char PRIV(utt_names)[] =
   STRING_prti0
   STRING_ps0
   STRING_psalterpahlavi0
+  STRING_qaac0
+  STRING_qaai0
   STRING_rejang0
   STRING_rjng0
   STRING_rohg0
@@ -796,7 +800,7 @@ const char PRIV(utt_names)[] =
   STRING_tifinagh0
   STRING_tirh0
   STRING_tirhuta0
-  STRING_tngs0
+  STRING_tnsa0
   STRING_toto0
   STRING_ugar0
   STRING_ugaritic0
@@ -1118,106 +1122,108 @@ const ucp_type_table PRIV(utt)[] = {
   { 1962, PT_SC, ucp_Inscriptional_Parthian },
   { 1967, PT_PC, ucp_Ps },
   { 1970, PT_SCX, ucp_Psalter_Pahlavi },
-  { 1985, PT_SC, ucp_Rejang },
+  { 1985, PT_SCX, ucp_Coptic },
-  { 1992, PT_SC, ucp_Rejang },
+  { 1990, PT_SC, ucp_Inherited },
-  { 1997, PT_SCX, ucp_Hanifi_Rohingya },
+  { 1995, PT_SC, ucp_Rejang },
-  { 2002, PT_SC, ucp_Runic },
+  { 2002, PT_SC, ucp_Rejang },
-  { 2008, PT_SC, ucp_Runic },
+  { 2007, PT_SCX, ucp_Hanifi_Rohingya },
-  { 2013, PT_GC, ucp_S },
+  { 2012, PT_SC, ucp_Runic },
-  { 2015, PT_SC, ucp_Samaritan },
+  { 2018, PT_SC, ucp_Runic },
+  { 2023, PT_GC, ucp_S },
   { 2025, PT_SC, ucp_Samaritan },
-  { 2030, PT_SC, ucp_Old_South_Arabian },
+  { 2035, PT_SC, ucp_Samaritan },
-  { 2035, PT_SC, ucp_Saurashtra },
+  { 2040, PT_SC, ucp_Old_South_Arabian },
-  { 2040, PT_SC, ucp_Saurashtra },
+  { 2045, PT_SC, ucp_Saurashtra },
-  { 2051, PT_PC, ucp_Sc },
+  { 2050, PT_SC, ucp_Saurashtra },
-  { 2054, PT_SC, ucp_SignWriting },
+  { 2061, PT_PC, ucp_Sc },
-  { 2059, PT_SCX, ucp_Sharada },
+  { 2064, PT_SC, ucp_SignWriting },
-  { 2067, PT_SC, ucp_Shavian },
+  { 2069, PT_SCX, ucp_Sharada },
-  { 2075, PT_SC, ucp_Shavian },
+  { 2077, PT_SC, ucp_Shavian },
-  { 2080, PT_SCX, ucp_Sharada },
+  { 2085, PT_SC, ucp_Shavian },
-  { 2085, PT_SC, ucp_Siddham },
+  { 2090, PT_SCX, ucp_Sharada },
-  { 2090, PT_SC, ucp_Siddham },
+  { 2095, PT_SC, ucp_Siddham },
-  { 2098, PT_SC, ucp_SignWriting },
+  { 2100, PT_SC, ucp_Siddham },
-  { 2110, PT_SCX, ucp_Khudawadi },
+  { 2108, PT_SC, ucp_SignWriting },
-  { 2115, PT_SCX, ucp_Sinhala },
+  { 2120, PT_SCX, ucp_Khudawadi },
-  { 2120, PT_SCX, ucp_Sinhala },
+  { 2125, PT_SCX, ucp_Sinhala },
-  { 2128, PT_PC, ucp_Sk },
+  { 2130, PT_SCX, ucp_Sinhala },
-  { 2131, PT_PC, ucp_Sm },
+  { 2138, PT_PC, ucp_Sk },
-  { 2134, PT_PC, ucp_So },
+  { 2141, PT_PC, ucp_Sm },
-  { 2137, PT_SCX, ucp_Sogdian },
+  { 2144, PT_PC, ucp_So },
-  { 2142, PT_SCX, ucp_Sogdian },
+  { 2147, PT_SCX, ucp_Sogdian },
-  { 2150, PT_SC, ucp_Old_Sogdian },
+  { 2152, PT_SCX, ucp_Sogdian },
-  { 2155, PT_SC, ucp_Sora_Sompeng },
+  { 2160, PT_SC, ucp_Old_Sogdian },
-  { 2160, PT_SC, ucp_Sora_Sompeng },
+  { 2165, PT_SC, ucp_Sora_Sompeng },
-  { 2172, PT_SC, ucp_Soyombo },
+  { 2170, PT_SC, ucp_Sora_Sompeng },
-  { 2177, PT_SC, ucp_Soyombo },
+  { 2182, PT_SC, ucp_Soyombo },
-  { 2185, PT_SC, ucp_Sundanese },
+  { 2187, PT_SC, ucp_Soyombo },
-  { 2190, PT_SC, ucp_Sundanese },
+  { 2195, PT_SC, ucp_Sundanese },
-  { 2200, PT_SCX, ucp_Syloti_Nagri },
+  { 2200, PT_SC, ucp_Sundanese },
-  { 2205, PT_SCX, ucp_Syloti_Nagri },
+  { 2210, PT_SCX, ucp_Syloti_Nagri },
-  { 2217, PT_SCX, ucp_Syriac },
+  { 2215, PT_SCX, ucp_Syloti_Nagri },
-  { 2222, PT_SCX, ucp_Syriac },
+  { 2227, PT_SCX, ucp_Syriac },
-  { 2229, PT_SCX, ucp_Tagalog },
+  { 2232, PT_SCX, ucp_Syriac },
-  { 2237, PT_SCX, ucp_Tagbanwa },
+  { 2239, PT_SCX, ucp_Tagalog },
-  { 2242, PT_SCX, ucp_Tagbanwa },
+  { 2247, PT_SCX, ucp_Tagbanwa },
-  { 2251, PT_SCX, ucp_Tai_Le },
+  { 2252, PT_SCX, ucp_Tagbanwa },
-  { 2257, PT_SC, ucp_Tai_Tham },
+  { 2261, PT_SCX, ucp_Tai_Le },
-  { 2265, PT_SC, ucp_Tai_Viet },
+  { 2267, PT_SC, ucp_Tai_Tham },
-  { 2273, PT_SCX, ucp_Takri },
+  { 2275, PT_SC, ucp_Tai_Viet },
-  { 2278, PT_SCX, ucp_Takri },
+  { 2283, PT_SCX, ucp_Takri },
-  { 2284, PT_SCX, ucp_Tai_Le },
+  { 2288, PT_SCX, ucp_Takri },
-  { 2289, PT_SC, ucp_New_Tai_Lue },
+  { 2294, PT_SCX, ucp_Tai_Le },
-  { 2294, PT_SCX, ucp_Tamil },
+  { 2299, PT_SC, ucp_New_Tai_Lue },
-  { 2300, PT_SCX, ucp_Tamil },
+  { 2304, PT_SCX, ucp_Tamil },
-  { 2305, PT_SC, ucp_Tangut },
+  { 2310, PT_SCX, ucp_Tamil },
-  { 2310, PT_SC, ucp_Tangsa },
+  { 2315, PT_SC, ucp_Tangut },
-  { 2317, PT_SC, ucp_Tangut },
+  { 2320, PT_SC, ucp_Tangsa },
-  { 2324, PT_SC, ucp_Tai_Viet },
+  { 2327, PT_SC, ucp_Tangut },
-  { 2329, PT_SCX, ucp_Telugu },
+  { 2334, PT_SC, ucp_Tai_Viet },
-  { 2334, PT_SCX, ucp_Telugu },
+  { 2339, PT_SCX, ucp_Telugu },
-  { 2341, PT_SC, ucp_Tifinagh },
+  { 2344, PT_SCX, ucp_Telugu },
-  { 2346, PT_SCX, ucp_Tagalog },
+  { 2351, PT_SC, ucp_Tifinagh },
-  { 2351, PT_SCX, ucp_Thaana },
+  { 2356, PT_SCX, ucp_Tagalog },
-  { 2356, PT_SCX, ucp_Thaana },
+  { 2361, PT_SCX, ucp_Thaana },
-  { 2363, PT_SC, ucp_Thai },
+  { 2366, PT_SCX, ucp_Thaana },
-  { 2368, PT_SC, ucp_Tibetan },
+  { 2373, PT_SC, ucp_Thai },
-  { 2376, PT_SC, ucp_Tibetan },
+  { 2378, PT_SC, ucp_Tibetan },
-  { 2381, PT_SC, ucp_Tifinagh },
+  { 2386, PT_SC, ucp_Tibetan },
-  { 2390, PT_SCX, ucp_Tirhuta },
+  { 2391, PT_SC, ucp_Tifinagh },
-  { 2395, PT_SCX, ucp_Tirhuta },
+  { 2400, PT_SCX, ucp_Tirhuta },
-  { 2403, PT_SC, ucp_Tangsa },
+  { 2405, PT_SCX, ucp_Tirhuta },
-  { 2408, PT_SC, ucp_Toto },
+  { 2413, PT_SC, ucp_Tangsa },
-  { 2413, PT_SC, ucp_Ugaritic },
+  { 2418, PT_SC, ucp_Toto },
-  { 2418, PT_SC, ucp_Ugaritic },
+  { 2423, PT_SC, ucp_Ugaritic },
-  { 2427, PT_SC, ucp_Unknown },
+  { 2428, PT_SC, ucp_Ugaritic },
-  { 2435, PT_SC, ucp_Vai },
+  { 2437, PT_SC, ucp_Unknown },
-  { 2439, PT_SC, ucp_Vai },
+  { 2445, PT_SC, ucp_Vai },
-  { 2444, PT_SC, ucp_Vithkuqi },
+  { 2449, PT_SC, ucp_Vai },
-  { 2449, PT_SC, ucp_Vithkuqi },
+  { 2454, PT_SC, ucp_Vithkuqi },
-  { 2458, PT_SC, ucp_Wancho },
+  { 2459, PT_SC, ucp_Vithkuqi },
-  { 2465, PT_SC, ucp_Warang_Citi },
+  { 2468, PT_SC, ucp_Wancho },
-  { 2470, PT_SC, ucp_Warang_Citi },
+  { 2475, PT_SC, ucp_Warang_Citi },
-  { 2481, PT_SC, ucp_Wancho },
+  { 2480, PT_SC, ucp_Warang_Citi },
-  { 2486, PT_ALNUM, 0 },
+  { 2491, PT_SC, ucp_Wancho },
-  { 2490, PT_SC, ucp_Old_Persian },
+  { 2496, PT_ALNUM, 0 },
-  { 2495, PT_PXSPACE, 0 },
+  { 2500, PT_SC, ucp_Old_Persian },
-  { 2499, PT_SPACE, 0 },
+  { 2505, PT_PXSPACE, 0 },
-  { 2503, PT_SC, ucp_Cuneiform },
+  { 2509, PT_SPACE, 0 },
-  { 2508, PT_UCNC, 0 },
+  { 2513, PT_SC, ucp_Cuneiform },
-  { 2512, PT_WORD, 0 },
+  { 2518, PT_UCNC, 0 },
-  { 2516, PT_SCX, ucp_Yezidi },
+  { 2522, PT_WORD, 0 },
-  { 2521, PT_SCX, ucp_Yezidi },
+  { 2526, PT_SCX, ucp_Yezidi },
-  { 2528, PT_SCX, ucp_Yi },
+  { 2531, PT_SCX, ucp_Yezidi },
-  { 2531, PT_SCX, ucp_Yi },
+  { 2538, PT_SCX, ucp_Yi },
-  { 2536, PT_GC, ucp_Z },
+  { 2541, PT_SCX, ucp_Yi },
-  { 2538, PT_SC, ucp_Zanabazar_Square },
+  { 2546, PT_GC, ucp_Z },
-  { 2554, PT_SC, ucp_Zanabazar_Square },
+  { 2548, PT_SC, ucp_Zanabazar_Square },
-  { 2559, PT_SC, ucp_Inherited },
+  { 2564, PT_SC, ucp_Zanabazar_Square },
-  { 2564, PT_PC, ucp_Zl },
+  { 2569, PT_SC, ucp_Inherited },
-  { 2567, PT_PC, ucp_Zp },
+  { 2574, PT_PC, ucp_Zl },
-  { 2570, PT_PC, ucp_Zs },
+  { 2577, PT_PC, ucp_Zp },
-  { 2573, PT_SC, ucp_Common },
+  { 2580, PT_PC, ucp_Zs },
-  { 2578, PT_SC, ucp_Unknown }
+  { 2583, PT_SC, ucp_Common },
+  { 2588, PT_SC, ucp_Unknown }
 };
 
 const size_t PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);