Infrastructure for building libucd.a.

.gitignore

+.*.swp
+
+# generated files:
+
+src/categories.cpp
+
+# intermediate files:
+
+.deps/
+.libs/
+.dirstamp
+
+*.pyc
+*.o
+*.lo
+
+# build output:
+
+src/libucd.la
+
+# autotools output:
+
+INSTALL
+NEWS
+README
+aclocal.m4
+autom4te.cache/
+config.guess
+config.h.in
+config.h
+config.log
+config.status
+config.sub
+configure
+depcomp
+install-sh
+libtool
+ltmain.sh
+m4/
+missing
+Makefile
+Makefile.in
+stamp-h1

Makefile.am

+AUTOMAKE_OPTIONS = subdir-objects
+
+localedir  = $(datadir)/locale
+xdgdatadir = @XDGDATADIR@
+mimedir    = $(xdgdatadir)/mime
+xmldir     = $(mimedir)/packages
+
+AM_LDFLAGS  = ${LTLIBINTL}
+AM_CXXFLAGS = -Isrc/include -Isrc
+
+ACLOCAL_AMFLAGS = -I m4
+
+bin_PROGRAMS =
+lib_LTLIBRARIES =
+man1_MANS =
+pkgdata_DATA =
+
+noinst_bin_PROGRAMS =
+noinst_LIBRARIES =
+
+noinst_bindir =
+
+EXTRA_DIST = config.rpath ChangeLog
+CLEANFILES =
+SUBDIRS =
+
+############################# libtool #########################################
+
+EXTRA_DIST += config.guess config.sub ltmain.sh
+
+# Increment if the interface has changed and is not backward compatible
+CURRENT=0
+
+# Increment  if source files have changed
+# Reset to 0 if the interface has changed
+REVISION=0
+
+# Increment  if the interface is backward compatible (superset)
+# Reset to 0 if the interface is not backward compatible
+AGE=0
+
+LIBUCD_VERSION=$(CURRENT):$(REVISION):$(AGE)
+
+############################# ChangeLog #######################################
+
+ChangeLog:
+	git log > ChangeLog
+
+dist-hook: ChangeLog
+
+.PHONY: ChangeLog
+
+EXTRA_DIST += ChangeLog
+
+############################# Unicode Character Database ######################
+
+src/categories.cpp: tools/categories.py
+	tools/categories.py ${UCD_ROOTDIR} > $@
+
+############################# libucd ##########################################
+
+libucd_includedir = $(includedir)/ucd
+libucd_include_HEADERS = \
+	src/include/ucd/ucd.h
+
+lib_LTLIBRARIES += src/libucd.la
+
+src_libucd_la_LDFLAGS = -version-info $(LIBUCD_VERSION)
+src_libucd_la_CXXFLAGS = ${AM_CXXFLAGS}
+src_libucd_la_SOURCES = \
+	src/categories.cpp

autogen.sh

+#!/bin/sh
+
+mkdir -p m4
+ln -sf README.md README
+ln -sf docs/ReleaseNotes.md NEWS
+
+aclocal -I m4 || exit 1
+
+libtoolize || exit 1
+autoheader || exit 1
+automake --add-missing || exit 1
+autoconf || exit 1

configure.ac

+AC_PREREQ([2.65])
+AC_INIT([Unicode Character Database Tools], [0.1], [https://github.com/rhdunn/ucd-tools/issues], [ucd-tools], [https://github.com/rhdunn/ucd-tools])
+AM_INIT_AUTOMAKE()
+
+m4_ifdef([AM_SILENT_RULES],[AM_SILENT_RULES])
+AM_SILENT_RULES([yes])
+
+AC_CONFIG_SRCDIR([src])
+AC_CONFIG_MACRO_DIR([m4])
+AC_CONFIG_HEADERS([config.h])
+
+LT_INIT
+
+dnl ================================================================
+dnl Program checks.
+dnl ================================================================
+
+AC_PROG_CXX
+AC_PROG_MAKE_SET
+AC_PROG_LIBTOOL
+
+dnl ================================================================
+dnl Generate output.
+dnl ================================================================
+
+AC_CONFIG_FILES([Makefile])
+AC_OUTPUT
+
+AC_MSG_NOTICE([
+
+    Configuration for Unicode Character Data Tools complete.
+
+        Source code location:          ${srcdir}
+        XDG data location:             ${XDGDATADIR}
+
+        Compiler:                      ${CXX}
+        Compiler flags:                ${CXXFLAGS}
+])

src/include/ucd/ucd.h

+/* Unicode Character Database API
+ *
+ * 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/>.
+ */
+
+#ifndef UNICODE_CHARACTER_DATA_H
+#define UNICODE_CHARACTER_DATA_H
+
+#include <stdint.h>
+
+/** @brief Unicode Character Database
+  */
+namespace ucd
+{
+	/** @brief Represents a Unicode codepoint.
+	  */
+	typedef uint32_t codepoint_t;
+
+	/** @brief Unicode General Category Values
+	  * @see   http://www.unicode.org/reports/tr44/
+	  */
+	enum category
+	{
+		// Other
+
+		Cc, /**< @brief Control Character */
+		Cf, /**< @brief Format Control Character */
+		Cn, /**< @brief Unassigned */
+		Co, /**< @brief Private Use */
+		Cs, /**< @brief Surrogate Code Point */
+
+		// Letter
+
+		Ll, /**< @brief Lower Case Letter */
+		Lm, /**< @brief Letter Modifier */
+		Lo, /**< @brief Other Letter */
+		Lt, /**< @brief Title Case Letter */
+		Lu, /**< @brief Upper Case Letter */
+
+		// Mark
+
+		Mc, /**< @brief Spacing Mark */
+		Me, /**< @brief Enclosing Mark */
+		Mn, /**< @brief Non-Spacing Mark */
+
+		// Symbol
+
+		Sc, /**< @brief Currency Symbol */
+		Sk, /**< @brief Modifier Symbol */
+		Sm, /**< @brief Math Symbol */
+		So, /**< @brief Other Symbol */
+
+		// Number
+
+		Nd, /**< @brief Decimal Digit */
+		Nl, /**< @brief Letter-Like Number */
+		No, /**< @brief Other Number */
+
+		// Punctuation
+
+		Pc, /**< @brief Connector */
+		Pd, /**< @brief Dash/Hyphen */
+		Pe, /**< @brief Close Punctuation Mark */
+		Pf, /**< @brief Final Quotation Mark */
+		Pi, /**< @brief Initial Quotation Mark */
+		Po, /**< @brief Other */
+		Ps, /**< @brief Open PUnctuation Mark */
+
+		// Separator
+
+		Zc, /**< @brief Whitespace character in the Cc category */
+		Zl, /**< @brief Line Separator */
+		Zp, /**< @brief Paragraph Separator */
+		Zs, /**< @brief Space Separator */
+	};
+
+	/** @brief Lookup the General Category for a Unicode codepoint.
+	  *
+	  * @param c The Unicode codepoint to lookup.
+	  * @return  The General Category of the Unicode codepoint.
+	  */
+	category lookup_category(codepoint_t c);
+}
+
+#endif

tools/categories.py

+#!/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]
+unicode_data = ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData')
+
+if __name__ == '__main__':
+	sys.stdout.write("""/* Unicode General Categories
+ *
+ * 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"
+
+using namespace ucd;
+""")
+
+	sys.stdout.write('\n')
+	sys.stdout.write('ucd::category ucd::lookup_category(codepoint_t c)\n')
+	sys.stdout.write('{\n')
+	sys.stdout.write('\treturn Cn;\n')
+	sys.stdout.write('}\n')