Add toupper, tolower and totitle case-conversion APIs.

Makefile.am

@@ -54,6 +54,9 @@ EXTRA_DIST += ChangeLog
 
 ############################# Unicode Character Database ######################
 
+src/case.cpp: tools/case.py tools/ucd.py
+	tools/case.py ${UCD_ROOTDIR} > $@
+
 src/categories.cpp: tools/categories.py tools/ucd.py
 	tools/categories.py ${UCD_ROOTDIR} > $@
 
@@ -68,5 +71,6 @@ lib_LTLIBRARIES += src/libucd.la
 src_libucd_la_LDFLAGS = -version-info $(LIBUCD_VERSION)
 src_libucd_la_CXXFLAGS = ${AM_CXXFLAGS}
 src_libucd_la_SOURCES = \
+	src/case.cpp \
 	src/categories.cpp \
 	src/ctype.cpp

src/include/ucd/ucd.h

@@ -31,6 +31,11 @@ namespace ucd
 	  */
 	typedef uint32_t codepoint_t;
 
+	/** @name  Unicode General Category
+	  * @brief These functions query the General Category property of Unicode codepoints.
+	  */
+	//@{
+
 	/** @brief Unicode General Category Groups
 	  * @see   http://www.unicode.org/reports/tr44/
 	  */
@@ -106,6 +111,7 @@ namespace ucd
 	category lookup_category(codepoint_t c);
 
 
+	//@}
 	/** @name  ctype-style APIs
 	  * @brief These functions provide wctype compatible functions using the UCD data.
 	  */
@@ -183,6 +189,50 @@ namespace ucd
 	int isupper(codepoint_t c);
 
 
+	//@}
+	/** @name  Case Conversion APIs
+	  * @brief These functions convert Unicode codepoints between lower, upper and title case.
+	  */
+	//@{
+
+
+	/** @brief Convert the Unicode codepoint to upper-case.
+	  *
+	  * This function only uses the simple case mapping present in the
+	  * UnicodeData file. The data in SpecialCasing requires Unicode
+	  * codepoints to be mapped to multiple codepoints.
+	  *
+	  * @param c The Unicode codepoint to convert.
+	  * @return  The upper-case Unicode codepoint for this codepoint, or
+	  *          this codepoint if there is no upper-case codepoint.
+	  */
+	codepoint_t toupper(codepoint_t c);
+
+	/** @brief Convert the Unicode codepoint to lower-case.
+	  *
+	  * This function only uses the simple case mapping present in the
+	  * UnicodeData file. The data in SpecialCasing requires Unicode
+	  * codepoints to be mapped to multiple codepoints.
+	  *
+	  * @param c The Unicode codepoint to convert.
+	  * @return  The lower-case Unicode codepoint for this codepoint, or
+	  *          this codepoint if there is no upper-case codepoint.
+	  */
+	codepoint_t tolower(codepoint_t c);
+
+	/** @brief Convert the Unicode codepoint to title-case.
+	  *
+	  * This function only uses the simple case mapping present in the
+	  * UnicodeData file. The data in SpecialCasing requires Unicode
+	  * codepoints to be mapped to multiple codepoints.
+	  *
+	  * @param c The Unicode codepoint to convert.
+	  * @return  The title-case Unicode codepoint for this codepoint, or
+	  *          this codepoint if there is no upper-case codepoint.
+	  */
+	codepoint_t totitle(codepoint_t c);
+
+
 	//@}
 }
 

tools/case.py

@@ -0,0 +1,100 @@
+#!/usr/bin/python
+
+# Copyright (C) 2012 Reece H. Dunn
+#
+# This file is part of ucd-tools.
+#
+# ucd-tools is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# ucd-tools is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with ucd-tools.  If not, see <http://www.gnu.org/licenses/>.
+
+import os
+import sys
+import ucd
+
+ucd_rootdir = sys.argv[1]
+ucd_version = ucd_rootdir.split('-')[-1]
+
+unicode_chars = {}
+null = ucd.CodePoint('0000')
+for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
+	if data['LowerCase'] != null or data['UpperCase'] != null or data['TitleCase'] != null:
+		unicode_chars[data['CodePoint']] = (data['LowerCase'], data['UpperCase'], data['TitleCase'])
+
+if __name__ == '__main__':
+	sys.stdout.write("""/* Unicode Case Conversion
+ *
+ * Copyright (C) 2012 Reece H. Dunn
+ *
+ * This file is part of ucd-tools.
+ *
+ * ucd-tools is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * ucd-tools is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with ucd-tools.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+// NOTE: This file is automatically generated from the UnicodeData.txt file in
+// the Unicode Character database by the ucd-tools/tools/categories.py script.
+
+#include "ucd/ucd.h"
+
+#include <stddef.h>
+
+using namespace ucd;
+
+// Unicode Character Data %s
+
+struct case_conversion_entry
+{
+	codepoint_t codepoint;
+	codepoint_t uppercase;
+	codepoint_t lowercase;
+	codepoint_t titlecase;
+};
+""" % ucd_version)
+
+	sys.stdout.write('\n')
+	sys.stdout.write('static const case_conversion_entry case_conversion_data[] =\n')
+	sys.stdout.write('{\n')
+	for codepoint in sorted(unicode_chars.keys()):
+		lower, upper, title = unicode_chars[codepoint]
+		sys.stdout.write('\t{ 0x%s, 0x%s, 0x%s, 0x%s },\n' % (codepoint, upper, lower, title))
+	sys.stdout.write('};\n')
+
+	for case in ['upper', 'lower', 'title']:
+		sys.stdout.write('\n')
+		sys.stdout.write('ucd::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('\twhile (begin <= end)\n')
+		sys.stdout.write('\t{\n')
+		sys.stdout.write('\t\tint pos = (begin + end) / 2;\n')
+		sys.stdout.write('\t\tconst case_conversion_entry *item = (case_conversion_data + pos);\n')
+		sys.stdout.write('\t\tif (c == item->codepoint)\n')
+		sys.stdout.write('\t\t\treturn item->%scase;\n' % case)
+		sys.stdout.write('\t\telse if (c > item->codepoint)\n')
+		sys.stdout.write('\t\t\tbegin = pos + 1;\n')
+		sys.stdout.write('\t\telse\n')
+		sys.stdout.write('\t\t\tend = pos - 1;\n')
+		sys.stdout.write('\t}\n')
+		sys.stdout.write('\treturn c;\n')
+		sys.stdout.write('}\n')

tools/ucd.py

@@ -70,7 +70,7 @@ def codepoint(x):
 	if ' ' in x:
 		return [CodePoint(c) for c in x.split()]
 	if x == '':
-		return None
+		return CodePoint('0000')
 	return CodePoint(x)
 
 def string(x):