Merge tag 'de5e36b4ad69c4acfdd728b2ca3e0e472d91afd1'

ucd-tools 11.0.0.1

src/ucd-tools/CHANGELOG.md

@@ -7,6 +7,10 @@ These are eSpeak NG specific modifications to the `ucd-tools` project:
 *  `data/espeak-ng` data files for eSpeak NG extended data.
 *  espeak-ng PropList property lookup as part of the `ucd_property` API.
 
+## 11.0.0.1 - 2021-05-04
+
+*  Fix -fsanitize=address issues in case.c.
+
 ## 11.0.0 - 2018-07-08
 
 *  Make the ispunct ctype compatibility implementation conformant.

src/ucd-tools/COPYING.UCD

@@ -1,8 +1,29 @@
+Unicode Data Files include all data files under the directories
+http://www.unicode.org/Public/, http://www.unicode.org/reports/,
+http://www.unicode.org/cldr/data/, http://source.icu-project.org/repos/icu/, and
+http://www.unicode.org/utility/trac/browser/.
+
+Unicode Data Files do not include PDF online code charts under the
+directory http://www.unicode.org/Public/.
+
+Software includes any source code published in the Unicode Standard
+or under the directories
+http://www.unicode.org/Public/, http://www.unicode.org/reports/,
+http://www.unicode.org/cldr/data/, http://source.icu-project.org/repos/icu/, and
+http://www.unicode.org/utility/trac/browser/.
+
+NOTICE TO USER: Carefully read the following legal agreement.
+BY DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING UNICODE INC.'S
+DATA FILES ("DATA FILES"), AND/OR SOFTWARE ("SOFTWARE"),
+YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE
+TERMS AND CONDITIONS OF THIS AGREEMENT.
+IF YOU DO NOT AGREE, DO NOT DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE
+THE DATA FILES OR SOFTWARE.
+
 COPYRIGHT AND PERMISSION NOTICE
 
-Copyright © 1991-2014 Unicode, Inc. All rights reserved.
-Distributed under the Terms of Use in 
-http://www.unicode.org/copyright.html.
+Copyright © 1991-2018 Unicode, Inc. All rights reserved.
+Distributed under the Terms of Use in http://www.unicode.org/copyright.html.
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of the Unicode data files and any associated documentation
@@ -11,14 +32,11 @@ a copy of the Unicode data files and any associated documentation
 without restriction, including without limitation the rights to use,
 copy, modify, merge, publish, distribute, and/or sell copies of
 the Data Files or Software, and to permit persons to whom the Data Files
-or Software are furnished to do so, provided that
-(a) this copyright and permission notice appear with all copies 
-of the Data Files or Software,
-(b) this copyright and permission notice appear in associated 
-documentation, and
-(c) there is clear notice in each modified Data File or in the Software
-as well as in the documentation associated with the Data File(s) or
-Software that the data or software has been modified.
+or Software are furnished to do so, provided that either
+(a) this copyright and permission notice appear with all copies
+of the Data Files or Software, or
+(b) this copyright and permission notice appear in associated
+Documentation.
 
 THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF
 ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE

src/ucd-tools/src/case.c

@@ -1,6 +1,6 @@
 /* Unicode Case Conversion
  *
- * Copyright (C) 2012-2018 Reece H. Dunn
+ * Copyright (C) 2012-2018, 2021 Reece H. Dunn
  *
  * This file is part of ucd-tools.
  *
@@ -19,7 +19,7 @@
  */
 
 /* NOTE: This file is automatically generated from the UnicodeData.txt file in
- * the Unicode Character database by the ucd-tools/tools/categories.py script.
+ * the Unicode Character database by the ucd-tools/tools/case.py script.
  */
 
 #include "ucd/ucd.h"
@@ -2822,7 +2822,7 @@ static const struct case_conversion_entry case_conversion_data[] =
 codepoint_t ucd_toupper(codepoint_t c)
 {
 	int begin = 0;
-	int end   = sizeof(case_conversion_data)/sizeof(case_conversion_data[0]);
+	int end   = sizeof(case_conversion_data)/sizeof(case_conversion_data[0]) - 1;
 	while (begin <= end)
 	{
 		int pos = (begin + end) / 2;
@@ -2840,7 +2840,7 @@ codepoint_t ucd_toupper(codepoint_t c)
 codepoint_t ucd_tolower(codepoint_t c)
 {
 	int begin = 0;
-	int end   = sizeof(case_conversion_data)/sizeof(case_conversion_data[0]);
+	int end   = sizeof(case_conversion_data)/sizeof(case_conversion_data[0]) - 1;
 	while (begin <= end)
 	{
 		int pos = (begin + end) / 2;
@@ -2858,7 +2858,7 @@ codepoint_t ucd_tolower(codepoint_t c)
 codepoint_t ucd_totitle(codepoint_t c)
 {
 	int begin = 0;
-	int end   = sizeof(case_conversion_data)/sizeof(case_conversion_data[0]);
+	int end   = sizeof(case_conversion_data)/sizeof(case_conversion_data[0]) - 1;
 	while (begin <= end)
 	{
 		int pos = (begin + end) / 2;

src/ucd-tools/tools/case.py

@@ -1,6 +1,6 @@
 #!/usr/bin/python
 
-# Copyright (C) 2012-2018 Reece H. Dunn
+# Copyright (C) 2012-2018, 2021 Reece H. Dunn
 #
 # This file is part of ucd-tools.
 #
@@ -33,7 +33,7 @@ for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
 if __name__ == '__main__':
 	sys.stdout.write("""/* Unicode Case Conversion
  *
- * Copyright (C) 2012-2018 Reece H. Dunn
+ * Copyright (C) 2012-2018, 2021 Reece H. Dunn
  *
  * This file is part of ucd-tools.
  *
@@ -52,7 +52,7 @@ if __name__ == '__main__':
  */
 
 /* NOTE: This file is automatically generated from the UnicodeData.txt file in
- * the Unicode Character database by the ucd-tools/tools/categories.py script.
+ * the Unicode Character database by the ucd-tools/tools/case.py script.
  */
 
 #include "ucd/ucd.h"
@@ -83,7 +83,7 @@ struct case_conversion_entry
 		sys.stdout.write('codepoint_t ucd_to%s(codepoint_t c)\n' % case)
 		sys.stdout.write('{\n')
 		sys.stdout.write('\tint begin = 0;\n')
-		sys.stdout.write('\tint end   = sizeof(case_conversion_data)/sizeof(case_conversion_data[0]);\n')
+		sys.stdout.write('\tint end   = sizeof(case_conversion_data)/sizeof(case_conversion_data[0]) - 1;\n')
 		sys.stdout.write('\twhile (begin <= end)\n')
 		sys.stdout.write('\t{\n')
 		sys.stdout.write('\t\tint pos = (begin + end) / 2;\n')