Unicode 9.0

Update from unicode charts 6.3 to unicode charts 9.0
fontforge · Sep 30, 2016 · d9aa90e · d9aa90e
1 parent 4368ab2
commit d9aa90e
Show file tree

Hide file tree

Showing 12 changed files with 837 additions and 752 deletions.
diff --git a/Unicode/ArabicForms.c b/Unicode/ArabicForms.c
@@ -2,7 +2,7 @@
 /* License: BSD-3-clause */
 /* Contributions: Khaled Hosny, Joe Da Silva */
 
-/* This file was generated using the program 'makeutype' */
+/* This file was generated using the program 'makeutype' for Unicode_version 9.0 */
 
 #include <utype.h>
 
@@ -13,7 +13,7 @@ struct arabicforms ArabicForms[] = {
 	{ 0x0602, 0x0602, 0x0602, 0x0602, 0, 0, 0 },
 	{ 0x0603, 0x0603, 0x0603, 0x0603, 0, 0, 0 },
 	{ 0x0604, 0x0604, 0x0604, 0x0604, 0, 0, 0 },
-	{ 0x0000, 0x0000, 0x0000, 0x0000, 0, 0, 0 },
+	{ 0x0605, 0x0605, 0x0605, 0x0605, 0, 0, 0 },
 	{ 0x0606, 0x0606, 0x0606, 0x0606, 0, 0, 0 },
 	{ 0x0607, 0x0607, 0x0607, 0x0607, 0, 0, 0 },
 	{ 0x0608, 0x0608, 0x0608, 0x0608, 0, 0, 0 },

diff --git a/Unicode/README.TXT b/Unicode/README.TXT
@@ -8,7 +8,7 @@ wget http://unicode.org/Public/UNIDATA/LineBreak.txt
 wget http://unicode.org/Public/UNIDATA/NamesList.txt
 wget http://unicode.org/Public/UNIDATA/PropList.txt
 wget http://unicode.org/Public/UNIDATA/UnicodeData.txt
-make makeutype
+gcc -s -I../inc -o makeutype makeutype.c
 ./makeutype
 rm *.txt
 mv utype.h ../inc/
@@ -38,18 +38,17 @@ wget http://unicode.org/Public/MAPPINGS/ISO8859/8859-14.TXT
 wget http://unicode.org/Public/MAPPINGS/ISO8859/8859-15.TXT
 wget http://unicode.org/Public/MAPPINGS/ISO8859/8859-16.TXT
 wget http://unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT
-mv KOI8-R.TXT koi8r.TXT
 wget http://unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/JIS0201.TXT
-mv JIS0201.TXT JIS0201.txt
 wget http://unicode.org/Public/MAPPINGS/VENDORS/ADOBE/zdingbat.txt
-mv zdingbat.txt zapfding.TXT
 wget http://unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/JIS0212.TXT
-wget http://unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ROMAN.TXT
-mv ROMAN.TXT MacRoman.TXT
+wget http://unicode.org/Public/MAPPINGS/VENDORS/APPLE/ROMAN.TXT
+wget http://unicode.org/Public/MAPPINGS/VENDORS/APPLE/SYMBOL.TXT
+wget http://unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT
+wget http://unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT
 wget http://unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/CYRILLIC.TXT
 mv CYRILLIC.TXT MacCYRILLIC.TXT
 
-gcc -s -o dump dump.c
+gcc -s -I../inc -o dump dump.c
 ./dump
 rm *.txt *.TXT
 

diff --git a/Unicode/charset/generate.sh b/Unicode/charset/generate.sh
@@ -58,9 +58,10 @@ uni_maps=(
 	"$u/VENDORS/MICSFT/WINDOWS/CP950.TXT"
 )
 
-a="ftp://ftp.oreilly.de/pub/examples/english_examples/nutshell/cjkv/adobe"
+#a="ftp://ftp.oreilly.de/pub/examples/english_examples/nutshell/cjkv/adobe"
+a="ftp://ftp.netbsd.org/pub/pkgsrc/distfiles/adobe-cmaps-20060615/"
 adobe_maps=(
-#	"$a/ac15.tar.Z"		# Big5
+	"$a/ac15.tar.Z"		# Big5
 	"$a/ag15.tar.Z"		# GB2312
 	"$a/aj16.tar.Z"		# JIS X 0208
 	"$a/aj20.tar.Z"		# JIS X 0212

diff --git a/Unicode/dump.c b/Unicode/dump.c
@@ -44,12 +44,13 @@
  * wget http://unicode.org/Public/MAPPINGS/ISO8859/8859-15.TXT
  * wget http://unicode.org/Public/MAPPINGS/ISO8859/8859-16.TXT
  * wget http://unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT
- * mv KOI8-R.TXT koi8r.TXT
  * wget http://unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/JIS0201.TXT
- * mv JIS0201.TXT JIS0201.txt
  * wget http://unicode.org/Public/MAPPINGS/VENDORS/ADOBE/zdingbat.txt
- * mv zdingbat.txt zapfding.TXT
  * wget http://unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/JIS0212.TXT
+ * wget http://unicode.org/Public/MAPPINGS/VENDORS/APPLE/ROMAN.TXT
+ * wget http://unicode.org/Public/MAPPINGS/VENDORS/APPLE/SYMBOL.TXT
+ * wget http://unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT
+ * wget http://unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT
  */
 
 #include <fontforge-config.h>
@@ -64,8 +65,8 @@
 char *alphabets[] = { "8859-1.TXT", "8859-2.TXT", "8859-3.TXT", "8859-4.TXT",
     "8859-5.TXT", "8859-6.TXT", "8859-7.TXT", "8859-8.TXT", "8859-9.TXT",
     "8859-10.TXT", "8859-11.TXT", "8859-13.TXT", "8859-14.TXT", "8859-15.TXT",
-    "8859-16.TXT", "koi8r.TXT", "JIS0201.txt", "WIN.TXT", "MacRoman.TXT",
-    "MacSYMBOL.TXT", "zapfding.TXT", /*"MacCYRILLIC.TXT",*/ NULL };
+    "8859-16.TXT", "KOI8-R.TXT", "JIS0201.TXT", "CP1252.TXT", "ROMAN.TXT",
+    "SYMBOL.TXT", "zdingbat.txt", /*"MacCYRILLIC.TXT",*/ NULL };
 char *alnames[] = { "i8859_1", "i8859_2", "i8859_3", "i8859_4",
     "i8859_5", "i8859_6", "i8859_7", "i8859_8", "i8859_9",
     "i8859_10", "i8859_11", "i8859_13", "i8859_14", "i8859_15",
@@ -78,7 +79,7 @@ int almaps[] = { em_iso8859_1, em_iso8859_2, em_iso8859_3, em_iso8859_4,
     -1 };
 
 
-char *cjk[] = { "JIS0208.TXT", "JIS0212.TXT", "BIG5.TXT", "GB2312.TXT",
+char *cjk[] = { "JIS0208.TXT", "JIS0212.TXT", "CP950.TXT", "GB2312.TXT",
 	"HANGUL.TXT", "Big5HKSCS.txt", NULL };
 /* I'm only paying attention to Wansung encoding (in HANGUL.TXT) which is 94x94 */
 /* I used to look at OLD5601, but that maps to Unicode 1.0, and Hangul's moved */

diff --git a/Unicode/is_Ligature.c b/Unicode/is_Ligature.c
@@ -5,7 +5,7 @@ License: BSD-3-clause
 Contributions:
 */
 
-/* This file was generated using the program 'makeutype' */
+/* This file was generated using the program 'makeutype' for Unicode_version 9.0 */
 
 #include "utype.h"
 #include <stdlib.h>
@@ -75,8 +75,12 @@ const uint16 ____ligature16[] = {
   0xfdba, 0xfdbb, 0xfdbc, 0xfdbd, 0xfdbe, 0xfdbf, 0xfdc0, 0xfdc1,
   0xfdc2, 0xfdc3, 0xfdc4, 0xfdc5, 0xfdc6, 0xfdc7, 0xfdf0, 0xfdf1,
   0xfdf2, 0xfdf3, 0xfdf4, 0xfdf5, 0xfdf6, 0xfdf7, 0xfdf8, 0xfdf9,
-  0xfdfa, 0xfdfb, 0xfdfd, 0xfe20, 0xfe21, 0xfef5, 0xfef6, 0xfef7,
-  0xfef8, 0xfef9, 0xfefa, 0xfefb, 0xfefc};
+  0xfdfa, 0xfdfb, 0xfdfd, 0xfe20, 0xfe21, 0xfe27, 0xfe28, 0xfef5,
+  0xfef6, 0xfef7, 0xfef8, 0xfef9, 0xfefa, 0xfefb, 0xfefc};
+
+const uint32 ____ligature32[] = {
+  0x00011176, 0x0001f670, 0x0001f671, 0x0001f672,
+  0x0001f673};
 
 const uint16 ____vulgfrac16[] = {
   0x00bc, 0x00bd, 0x00be, 0x2150, 0x2151, 0x2152, 0x2153, 0x2154,
@@ -85,11 +89,15 @@ const uint16 ____vulgfrac16[] = {
 
 const uint16 ____fraction16[] = {
   0x0b72, 0x0b73, 0x0b74, 0x0b75, 0x0b76, 0x0b77, 0x0c78, 0x0c79,
-  0x0c7a, 0x0c7b, 0x0c7c, 0x0c7d, 0x0c7e, 0x0d73, 0x0d74, 0x0d75,
-  0x2044, 0x215f, 0x2cfd, 0xa830, 0xa831, 0xa832, 0xa833, 0xa834,
-  0xa835};
+  0x0c7a, 0x0c7b, 0x0c7c, 0x0c7d, 0x0c7e, 0x0d58, 0x0d59, 0x0d5a,
+  0x0d5b, 0x0d5c, 0x0d5d, 0x0d5e, 0x0d73, 0x0d74, 0x0d75, 0x0d76,
+  0x0d77, 0x0d78, 0x2044, 0x215f, 0x2cfd, 0xa830, 0xa831, 0xa832,
+  0xa833, 0xa834, 0xa835};
 
 const uint32 ____fraction32[] = {
+  0x000109bc, 0x000109bd, 0x000109f6, 0x000109f7,
+  0x000109f8, 0x000109f9, 0x000109fa, 0x000109fb,
+  0x000109fc, 0x000109fd, 0x000109fe, 0x000109ff,
   0x00010e7b, 0x00010e7c, 0x00010e7d, 0x00010e7e};
 
 static int compare_codepoints16(const void *uCode1, const void *uCode2) {
@@ -105,25 +113,28 @@ static int compare_codepoints32(const void *uCode1, const void *uCode2) {
 }
 
 int LigatureCount(void) {
-    return( 509 );
+    return( 516 );
 }
 
 int VulgarFractionCount(void) {
     return( 19 );
 }
 
 int OtherFractionCount(void) {
-    return( 29 );
+    return( 51 );
 }
 
 int FractionCount(void) {
-    return( 48 );
+    return( 70 );
 }
 
 int32 Ligature_get_U(int n) {
-    if ( n<0 || n>=509 )
+    if ( n<0 || n>=516 )
 	return( -1 );
-    return( (int32)(____ligature16[n]) );
+    if ( n<511 )
+	return( (int32)(____ligature16[n]) );
+    else
+	return( (int32)(____ligature32[n-511]) );
 }
 
 int32 VulgFrac_get_U(int n) {
@@ -133,24 +144,31 @@ int32 VulgFrac_get_U(int n) {
 }
 
 int32 Fraction_get_U(int n) {
-    if ( n<0 || n>=29 )
+    if ( n<0 || n>=51 )
 	return( -1 );
-    if ( n<25 )
+    if ( n<35 )
 	return( (int32)(____fraction16[n]) );
     else
-	return( (int32)(____fraction32[n-25]) );
+	return( (int32)(____fraction32[n-35]) );
 }
 
 int Ligature_find_N(uint32 uCode) {
     uint16 uCode16, *p16;
+    uint32 *p32;
     int n=-1;
 
-    if ( uCode<0x132 || uCode>0xfefc || isligorfrac(uCode)==0 )
+    if ( uCode<0x132 || uCode>0x1f673 || (uCode<65536 && isligorfrac(uCode)==0) )
 	return( -1 );
-    uCode16 = uCode;
-    p16 = (uint16 *)(bsearch(&uCode16, ____ligature16, 509, \
+    if ( uCode<0xfefc ) {
+	uCode16 = uCode;
+	p16 = (uint16 *)(bsearch(&uCode16, ____ligature16, 511, \
 				sizeof(uint16), compare_codepoints16));
-    if ( p16 ) n = p16 - ____ligature16;
+	if ( p16 ) n = p16 - ____ligature16;
+    } else {
+	p32 = (uint32 *)(bsearch(&uCode, ____ligature32, 5, \
+				sizeof(uint32), compare_codepoints32));
+	if ( p32 ) n = p32 - ____ligature32 + 511;
+    }
     return( n );
 }
 
@@ -174,15 +192,15 @@ int Fraction_find_N(uint32 uCode) {
 
     if ( uCode<0xb72 || uCode>0x10e7e || (uCode<65536 && isligorfrac(uCode)==0) )
 	return( -1 );
-    if ( uCode<25 ) {
+    if ( uCode<0xa835 ) {
 	uCode16 = uCode;
-	p16 = (uint16 *)(bsearch(&uCode16, ____fraction16, 25, \
+	p16 = (uint16 *)(bsearch(&uCode16, ____fraction16, 35, \
 				sizeof(uint16), compare_codepoints16));
 	if ( p16 ) n = p16 - ____fraction16;
     } else {
-	p32 = (uint32 *)(bsearch(&uCode, ____fraction32, 4, \
+	p32 = (uint32 *)(bsearch(&uCode, ____fraction32, 16, \
 				sizeof(uint32), compare_codepoints32));
-	if ( p32 ) n = p32 - ____fraction32 + 25;
+	if ( p32 ) n = p32 - ____fraction32 + 35;
     }
     return( n );
 }

diff --git a/Unicode/makebuildtables.c b/Unicode/makebuildtables.c
@@ -30,6 +30,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <utype.h>
+#include "utype.c"
 
 #define ACUTE		0x1
 #define GRAVE		0x2

diff --git a/Unicode/makeutype.c b/Unicode/makeutype.c
@@ -42,8 +42,8 @@
  * Run "gcc -s -I../inc -o makeutype makeutype.c"
  *
  * Then run the executable binary "/makeutype".
- * This will create 4 files in the same directory:
- *	ArabicForms.c, unialt.c, utype.c, utype.h
+ * This will create 5 files in the same directory:
+ *	ArabicForms.c, is_Ligatures.c, unialt.c, utype.c, utype.h
  * (please move utype.h into Fontforge's "../inc" subdirectory)
  *
  * When done building the updated files, you can clean-up by removing
@@ -52,6 +52,8 @@
  */
 #include <fontforge-config.h>
 
+#define UnicodeMajor	9
+#define UnicodeMinor	0
 
 /* Build a ctype array out of the UnicodeData.txt and PropList.txt files */
 #include <stdio.h>
@@ -137,7 +139,7 @@ unsigned long ligature[LG_MAX];
 unsigned long fraction[FR_MAX];
 unsigned long vulgfrac[VF_MAX];
 
-const char GeneratedFileMessage[] = "\n/* This file was generated using the program 'makeutype' */\n\n";
+const char GeneratedFileMessage[] = "\n/* This file was generated using the program 'makeutype' for Unicode_version %d.%d */\n\n";
 const char CantReadFile[] = "Can't find or read file %s\n";		/* exit(1) */
 const char CantSaveFile[] = "Can't open or write to output file %s\n";	/* exit(2) */
 const char NoMoreMemory[] = "Can't access more memory.\n";		/* exit(3) */
@@ -664,7 +666,7 @@ static void dumparabicdata(FILE *header) {
     fprintf( data, "/* Copyright: 2001 George Williams */\n" );
     fprintf( data, "/* License: BSD-3-clause */\n" );
     fprintf( data, "/* Contributions: Khaled Hosny, Joe Da Silva */\n" );
-    fprintf( data, GeneratedFileMessage );
+    fprintf( data, GeneratedFileMessage, UnicodeMajor, UnicodeMinor );
 
     fprintf( data, "#include <utype.h>\n\n" );
 
@@ -760,7 +762,7 @@ static void dumpbsearchfindN(FILE *data,long unsigned int *dt,int s,int m,char *
 	fprintf( data, "(uCode<%d && isligorfrac(uCode)==0) )\n", MAXC );
     fprintf( data, "\treturn( -1 );\n    " );
     if ( s<m )
-	fprintf( data, "if ( uCode<%d ) {\n\tuCode16 = uCode;\n\t", s );
+	fprintf( data, "if ( uCode<0x%x ) {\n\tuCode16 = uCode;\n\t", dt[s-1] );
     else
 	fprintf( data, "uCode16 = uCode;\n    " );
     fprintf( data, "p16 = (uint16 *)(bsearch(&uCode16, %s16, %d, \\\n", t, s );
@@ -824,7 +826,7 @@ static void dumpligaturesfractions(FILE *header) {
     fprintf( data, "Copyright: 2016 Joe Da Silva\n" );
     fprintf( data, "License: BSD-3-clause\n" );
     fprintf( data, "Contributions:\n*/\n" );
-    fprintf( data, GeneratedFileMessage );
+    fprintf( data, GeneratedFileMessage, UnicodeMajor, UnicodeMinor );
     fprintf( data, "#include \"utype.h\"\n" );
     fprintf( data, "#include <stdlib.h>\n\n" );
 
@@ -901,7 +903,7 @@ static void dump() {
     fprintf( header, "/* Copyright: 2001 George Williams */\n" );
     fprintf( header, "/* License: BSD-3-clause */\n" );
     fprintf( header, "/* Contributions: Joe Da Silva */\n" );
-    fprintf( header, GeneratedFileMessage );
+    fprintf( header, GeneratedFileMessage, UnicodeMajor, UnicodeMinor );
 
     fprintf( header, "#include <ctype.h>\t/* Include here so we can control it. If a system header includes it later bad things happen */\n" );
     fprintf( header, "#include <basics.h>\t/* Include here so we can use pre-defined int types to correctly size constant data arrays. */\n" );
@@ -1049,7 +1051,7 @@ static void dump() {
     fprintf( data, "/* License: BSD-3-clause */\n" );
     fprintf( data, "/* Contributions: Werner Lemberg, Khaled Hosny, Joe Da Silva */\n\n" );
     fprintf( data, "#include \"utype.h\"\n" );
-    fprintf( data, GeneratedFileMessage );
+    fprintf( data, GeneratedFileMessage, UnicodeMajor, UnicodeMinor );
     fprintf( data, "const unsigned short ____tolower[]= { 0,\n" );
     for ( i=0; i<MAXC; i+=j ) {
 	fprintf( data, " " );
@@ -1197,7 +1199,7 @@ return;
 
     fprintf(file, "#include <chardata.h>\n" );
 
-    fprintf(file, GeneratedFileMessage );
+    fprintf(file, GeneratedFileMessage, UnicodeMajor, UnicodeMinor );
 
     for ( i=32; i<MAXC; ++i ) {
 	if ( alts[i][0]!=0 ) {