F8D0-D8FF: Klingon

Makefile.am

@@ -76,14 +76,17 @@ data/ucd/UnicodeData.txt:
 ############################# libucd ##########################################
 
 src/case.cpp: tools/case.py tools/ucd.py \
+	supplemental/Klingon.txt \
 	data/ucd/UnicodeData.txt
 	tools/case.py ${UCD_ROOTDIR} ${UCD_VERSION} > $@
 
 src/categories.cpp: tools/categories.py tools/ucd.py \
+	supplemental/Klingon.txt \
 	data/ucd/UnicodeData.txt
 	tools/categories.py ${UCD_ROOTDIR} ${UCD_VERSION} > $@
 
 src/scripts.cpp: tools/scripts.py tools/ucd.py \
+	supplemental/Klingon.txt \
 	data/language-subtag-registry \
 	data/ucd/Scripts.txt
 	tools/scripts.py ${UCD_ROOTDIR} ${UCD_VERSION} > $@
@@ -108,8 +111,10 @@ tests_printucddata_SOURCES = tests/printucddata.cpp
 tests_printucddata_LDADD   = src/libucd.la
 
 tests/unicode-data.expected: tools/printdata.py tools/ucd.py \
+	supplemental/Klingon.txt \
 	data/ucd/UnicodeData.txt \
-	data/ucd/PropList.txt
+	data/ucd/PropList.txt \
+	data/ucd/Scripts.txt
 	tools/printdata.py ${UCD_ROOTDIR} > $@
 
 tests/unicode-data.actual: tests/printucddata

src/categories.cpp

@@ -1249,6 +1249,26 @@ static const uint8_t categories_00D700[256] =
 	/* F0 */ Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Cn, Cn, Cn, Cn,
 };
 
+static const uint8_t categories_00F800[256] =
+{
+	/* 00 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 10 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 20 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 30 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 40 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 50 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 60 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 70 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 80 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* 90 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* A0 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* B0 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* C0 */ Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co, Co,
+	/* D0 */ Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo,
+	/* E0 */ Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Co, Co, Co, Co, Co, Co,
+	/* F0 */ Nd, Nd, Nd, Nd, Nd, Nd, Nd, Nd, Nd, Nd, Co, Co, Co, Po, Po, So,
+};
+
 static const uint8_t categories_00FA00[256] =
 {
 	/* 00 */ Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo, Lo,
@@ -2429,8 +2449,9 @@ static const uint8_t *categories_000000_00D7FF[] =
 	categories_00D700,
 };
 
-static const uint8_t *categories_00F900_02FAFF[] =
+static const uint8_t *categories_00F800_02FAFF[] =
 {
+	categories_00F800,
 	categories_Lo, // 00F900
 	categories_00FA00,
 	categories_00FB00,
@@ -2961,10 +2982,10 @@ ucd::category ucd::lookup_category(codepoint_t c)
 		return (ucd::category)table[c % 256];
 	}
 	if (c <= 0x00DFFF) return Cs; // 00D800..00DFFF : Surrogates
-	if (c <= 0x00F8FF) return Co; // 00E000..00F8FF : Private Use Area
-	if (c <= 0x02FAFF) // 00F900..02FAFF
+	if (c <= 0x00F7FF) return Co; // 00E000..00F7FF : Private Use Area
+	if (c <= 0x02FAFF) // 00F800..02FAFF
 	{
-		const uint8_t *table = categories_00F900_02FAFF[(c - 0x00F900) / 256];
+		const uint8_t *table = categories_00F800_02FAFF[(c - 0x00F800) / 256];
 		return (ucd::category)table[c % 256];
 	}
 	if (c <= 0x0DFFFF) return Cn; // 02FB00..0DFFFF : Unassigned

src/include/ucd/ucd.h

@@ -202,6 +202,7 @@ namespace ucd
 		Phnx, /**< @brief Phoenician Script */
 		Plrd, /**< @brief Miao Script */
 		Prti, /**< @brief Inscriptional Parthian Script */
+		Qaak, /**< @brief Klingon Script */
 		Rjng, /**< @brief Rejang Script */
 		Runr, /**< @brief Runic Script */
 		Samr, /**< @brief Samaritan Script */

src/scripts.cpp

@@ -1309,6 +1309,26 @@ static const uint8_t scripts_00D700[256] =
 	/* F0 */ Hang, Hang, Hang, Hang, Hang, Hang, Hang, Hang, Hang, Hang, Hang, Hang, Zzzz, Zzzz, Zzzz, Zzzz,
 };
 
+static const uint8_t scripts_00F800[256] =
+{
+	/* 00 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 10 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 20 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 30 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 40 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 50 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 60 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 70 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 80 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* 90 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* A0 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* B0 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* C0 */ Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* D0 */ Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak,
+	/* E0 */ Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz, Zzzz,
+	/* F0 */ Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Qaak, Zzzz, Zzzz, Zzzz, Zyyy, Zyyy, Zyyy,
+};
+
 static const uint8_t scripts_00FA00[256] =
 {
 	/* 00 */ Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant, Hant,
@@ -2489,8 +2509,9 @@ static const uint8_t *scripts_000000_00D7FF[] =
 	scripts_00D700,
 };
 
-static const uint8_t *scripts_00F900_02FAFF[] =
+static const uint8_t *scripts_00F800_02FAFF[] =
 {
+	scripts_00F800,
 	scripts_Hant, // 00F900
 	scripts_00FA00,
 	scripts_00FB00,
@@ -3020,10 +3041,10 @@ ucd::script ucd::lookup_script(codepoint_t c)
 		const uint8_t *table = scripts_000000_00D7FF[(c - 0x000000) / 256];
 		return (ucd::script)table[c % 256];
 	}
-	if (c <= 0x00F8FF) return Zzzz; // 00D800..00F8FF : Surrogates / Private Use Area
-	if (c <= 0x02FAFF) // 00F900..02FAFF
+	if (c <= 0x00F7FF) return Zzzz; // 00D800..00F7FF : Surrogates / Private Use Area
+	if (c <= 0x02FAFF) // 00F800..02FAFF
 	{
-		const uint8_t *table = scripts_00F900_02FAFF[(c - 0x00F900) / 256];
+		const uint8_t *table = scripts_00F800_02FAFF[(c - 0x00F800) / 256];
 		return (ucd::script)table[c % 256];
 	}
 	if (c <= 0x0DFFFF) return Zzzz; // 02FB00..0DFFFF : Unassigned

supplemental/Klingon.txt

@@ -0,0 +1,41 @@
+# Code Point ; Script ; General Category ; Name ; Okrand Transliteration
+
+F8D0;Qaak;Lo;KLINGON LETTER A;a
+F8D1;Qaak;Lo;KLINGON LETTER B;a
+F8D2;Qaak;Lo;KLINGON LETTER CH;ch
+F8D3;Qaak;Lo;KLINGON LETTER D;D
+F8D4;Qaak;Lo;KLINGON LETTER E;e
+F8D5;Qaak;Lo;KLINGON LETTER GH;gh
+F8D6;Qaak;Lo;KLINGON LETTER H;H
+F8D7;Qaak;Lo;KLINGON LETTER I;I
+F8D8;Qaak;Lo;KLINGON LETTER J;j
+F8D9;Qaak;Lo;KLINGON LETTER L;l
+F8DA;Qaak;Lo;KLINGON LETTER M;m
+F8DB;Qaak;Lo;KLINGON LETTER N;n
+F8DC;Qaak;Lo;KLINGON LETTER NG;ng
+F8DD;Qaak;Lo;KLINGON LETTER O;o
+F8DE;Qaak;Lo;KLINGON LETTER P;p
+F8DF;Qaak;Lo;KLINGON LETTER Q;q
+F8E0;Qaak;Lo;KLINGON LETTER QH;Q
+F8E1;Qaak;Lo;KLINGON LETTER R;r
+F8E2;Qaak;Lo;KLINGON LETTER S;S
+F8E3;Qaak;Lo;KLINGON LETTER T;t
+F8E4;Qaak;Lo;KLINGON LETTER TLH;tlh
+F8E5;Qaak;Lo;KLINGON LETTER U;u
+F8E6;Qaak;Lo;KLINGON LETTER V;v
+F8E7;Qaak;Lo;KLINGON LETTER W;w
+F8E8;Qaak;Lo;KLINGON LETTER Y;y
+F8E9;Qaak;Lo;KLINGON LETTER GLOTTAL STOP;'
+F8F0;Qaak;Nd;KLINGON DIGIT ZERO;0
+F8F1;Qaak;Nd;KLINGON DIGIT ONE;1
+F8F2;Qaak;Nd;KLINGON DIGIT TWO;2
+F8F3;Qaak;Nd;KLINGON DIGIT THREE;3
+F8F4;Qaak;Nd;KLINGON DIGIT FOUR;4
+F8F5;Qaak;Nd;KLINGON DIGIT FIVE;5
+F8F6;Qaak;Nd;KLINGON DIGIT SIX;6
+F8F7;Qaak;Nd;KLINGON DIGIT SEVEN;7
+F8F8;Qaak;Nd;KLINGON DIGIT EIGHT;8
+F8F9;Qaak;Nd;KLINGON DIGIT NINE;9
+F8FD;Zyyy;Po;KLINGON COMMA;,
+F8FE;Zyyy;Po;KLINGON FULL STOP;.
+F8FF;Zyyy;So;KLINGON MUMMIFICATION GLYPH;

tests/printucddata.cpp

@@ -154,6 +154,7 @@ const char *get_script_string(ucd::script s)
 	case Phnx: return "Phnx";
 	case Plrd: return "Plrd";
 	case Prti: return "Prti";
+	case Qaak: return "Qaak";
 	case Rjng: return "Rjng";
 	case Runr: return "Runr";
 	case Samr: return "Samr";

tools/categories.py

@@ -28,6 +28,9 @@ unicode_chars = {}
 for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
 	for codepoint in data['CodePoint']:
 		unicode_chars[codepoint] = data['GeneralCategory']
+for data in ucd.parse_ucd_data('supplemental', 'Klingon'):
+	for codepoint in data['CodePoint']:
+		unicode_chars[codepoint] = data['GeneralCategory']
 
 # This map is a combination of the information in the UnicodeData and Blocks
 # data files. It is intended to reduce the number of character tables that
@@ -35,8 +38,8 @@ for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
 category_sets = [
 	(ucd.CodeRange('000000..00D7FF'), None, 'Multiple Blocks'),
 	(ucd.CodeRange('00D800..00DFFF'), 'Cs', 'Surrogates'),
-	(ucd.CodeRange('00E000..00F8FF'), 'Co', 'Private Use Area'),
-	(ucd.CodeRange('00F900..02FAFF'), None, 'Multiple Blocks'),
+	(ucd.CodeRange('00E000..00F7FF'), 'Co', 'Private Use Area'),
+	(ucd.CodeRange('00F800..02FAFF'), None, 'Multiple Blocks'),
 	(ucd.CodeRange('02FB00..0DFFFF'), 'Cn', 'Unassigned'),
 	(ucd.CodeRange('0E0000..0E01FF'), None, 'Multiple Blocks'),
 	(ucd.CodeRange('0E0200..0EFFFF'), 'Cn', 'Unassigned'),

tools/printdata.py

@@ -35,6 +35,13 @@ for data in ucd.parse_ucd_data(ucd_rootdir, 'PropList'):
 for data in ucd.parse_ucd_data(ucd_rootdir, 'Scripts'):
 	for codepoint in data['Range']:
 		unicode_chars[codepoint]['Script'] = data['Script']
+for data in ucd.parse_ucd_data('supplemental', 'Klingon'):
+	for codepoint in data['CodePoint']:
+		unicode_chars[codepoint] = data
+		unicode_chars[codepoint]['Properties'] = []
+		unicode_chars[codepoint]['UpperCase'] = ucd.CodePoint('0000')
+		unicode_chars[codepoint]['LowerCase'] = ucd.CodePoint('0000')
+		unicode_chars[codepoint]['TitleCase'] = ucd.CodePoint('0000')
 
 null = ucd.CodePoint('0000')
 if __name__ == '__main__':

tools/scripts.py

@@ -28,14 +28,17 @@ unicode_chars = {}
 for data in ucd.parse_ucd_data(ucd_rootdir, 'Scripts'):
 	for codepoint in data['Range']:
 		unicode_chars[codepoint] = data['Script']
+for data in ucd.parse_ucd_data('supplemental', 'Klingon'):
+	for codepoint in data['CodePoint']:
+		unicode_chars[codepoint] = data['Script']
 
 # This map is a combination of the information in the UnicodeData and Blocks
 # data files. It is intended to reduce the number of character tables that
 # need to be generated.
 script_sets = [
 	(ucd.CodeRange('000000..00D7FF'), None,   'Multiple Blocks'),
-	(ucd.CodeRange('00D800..00F8FF'), 'Zzzz', 'Surrogates / Private Use Area'),
-	(ucd.CodeRange('00F900..02FAFF'), None,   'Multiple Blocks'),
+	(ucd.CodeRange('00D800..00F7FF'), 'Zzzz', 'Surrogates / Private Use Area'),
+	(ucd.CodeRange('00F800..02FAFF'), None,   'Multiple Blocks'),
 	(ucd.CodeRange('02FB00..0DFFFF'), 'Zzzz', 'Unassigned'),
 	(ucd.CodeRange('0E0000..0E01FF'), None,   'Multiple Blocks'),
 	(ucd.CodeRange('0E0200..10FFFF'), 'Zzzz', 'Unassigned'),

tools/ucd.py

@@ -147,6 +147,14 @@ data_items = {
 		('LowerCase', codepoint),
 		('TitleCase', codepoint),
 	],
+	# Supplemental Data:
+	'Klingon': [
+		('CodePoint', codepoint),
+		('Script', str),
+		('GeneralCategory', string),
+		('Name', string),
+		('Transliteration', string),
+	],
 }
 
 def parse_ucd_data(ucd_rootdir, dataset):