Gave the whole thing an (explicit) BSD style LICENSE and got swig (ut…

…f) to work.

.gitignore

@@ -5,4 +5,6 @@
 *.inc
 *.lo
 *.o
-depend
+depend
+*.la
+header.txt

LICENSE

@@ -0,0 +1,26 @@
+Copyright (c) 2012 Diedrich Vorberg <diedrich@tux4web.de>
+
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+o Redistributions of source code must retain the above copyright
+  notice, this list of conditions and the following disclaimer.
+
+o Redistributions in binary form must reproduce the above copyright
+  notice, this list of conditions and the following disclaimer in the
+  documentation and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

Makefile

@@ -1,7 +1,7 @@
 include flags.mak
 
 # The sources for the library
-SRCS=betacode_greek.c++ cjhebrew.c++
+SRCS=betacode_greek.c++ cjhebrew.c++ conversion.c++
 OBJS=$(SRCS:%.c++=%.o) code_tables.o
 
 CODE_LISTS=coptic.tbl greek_asterisk.tbl greek_case.tbl\

betacode_greek.c++

@@ -1,9 +1,24 @@
+// -*- mode: c++; encoding: utf-8; -*_
+//
+// This file is part of libtransliterate
+//
+// Copyright 2012 by Diedrich Vorberg <diedrich@tux4web.de>
+//
+// All Rights Reserved.
+//
+// For more Information on orm see the README and LICENSE file.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+// CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+// INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED.
+
 #include <string.h>
 #include <stdlib.h>
 #include <stdio.h>
 
 #include "trie.h"
-#include "util.h"
 #include "code_tables.h"
 
 class forward_greek_trie: public trie<char, uint16_t>, public code_container

cjhebrew.c++

@@ -1,9 +1,24 @@
+// -*- mode: c++; encoding: utf-8; -*_
+//
+// This file is part of libtransliterate
+//
+// Copyright 2012 by Diedrich Vorberg <diedrich@tux4web.de>
+//
+// All Rights Reserved.
+//
+// For more Information on orm see the README and LICENSE file.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+// CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+// INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED.
+
 #include <string.h>
 #include <stdlib.h>
 #include <stdio.h>
 
 #include "trie.h"
-#include "util.h"
 #include "code_tables.h"
 
 class cjhebrew_to_utf16_trie_t:

cjhebrew.tbl

@@ -1,3 +1,19 @@
+// -*- mode: fundamental; encoding: utf-8; -*_
+//
+// This file is part of libtransliterate
+//
+// Copyright 2012 by Diedrich Vorberg <diedrich@tux4web.de>
+//
+// All Rights Reserved.
+//
+// For more Information on orm see the README and LICENSE file.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+// CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+// INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED.
+
 // o Syntax: Everything after // is ignored.
 // o Empty lines are ignored
 // o Everything else must be <code> <code point>

code_tables.c++

@@ -1,3 +1,19 @@
+// -*- mode: c++; encoding: utf-8; -*_
+//
+// This file is part of libtransliterate
+//
+// Copyright 2012 by Diedrich Vorberg <diedrich@tux4web.de>
+//
+// All Rights Reserved.
+//
+// For more Information on orm see the README and LICENSE file.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+// CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+// INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED.
+
 #include "code_tables.h"
 
 void add_greek_asterisk_code_table(code_container *container)

code_tables.h

@@ -1,3 +1,19 @@
+// -*- mode: c++; encoding: utf-8; -*_
+//
+// This file is part of libtransliterate
+//
+// Copyright 2012 by Diedrich Vorberg <diedrich@tux4web.de>
+//
+// All Rights Reserved.
+//
+// For more Information on orm see the README and LICENSE file.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+// CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+// INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED.
+
 #include <stdint.h>
 
 /* This header defines a mix-in class that allows an object to be passed to

conversion.c++

@@ -1,10 +1,214 @@
+// -*- mode: c++; encoding: utf-8; -*_
+//
+// This file is part of libtransliterate
+//
+// This is based on utf8.h and utf8.c written by Alexey Vatchenko.
+//
+
+/*
+ * Copyright (c) 2007 Alexey Vatchenko <av@bsdua.org>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
 #include <stdint.h>
+#include <sys/types.h>
+#include <wchar.h>
+
+#define UTF8_IGNORE_ERROR		0x01
+#define UTF8_SKIP_BOM			0x02
+
+#define _NXT	0x80
+#define _SEQ2	0xc0
+#define _SEQ3	0xe0
+#define _SEQ4	0xf0
+#define _SEQ5	0xf8
+#define _SEQ6	0xfc
+
+#define _BOM	0xfeff
+
+static int
+__wchar_forbitten(wchar_t sym)
+{
+
+	/* Surrogate pairs */
+	if (sym >= 0xd800 && sym <= 0xdfff)
+		return (-1);
+
+	return (0);
+}
+
+static int
+__utf8_forbitten(u_char octet)
+{
+
+	switch (octet) {
+	case 0xc0:
+	case 0xc1:
+	case 0xf5:
+	case 0xff:
+		return (-1);
+	}
+
+	return (0);
+}
 
 namespace transliterate
 {
     size_t utf16_to_utf8(uint16_t *input, char *buffer,
                          size_t buffer_length)
     {
+/*
+ * DESCRIPTION
+ *	This function translates UCS-4 symbols (given in local machine
+ *	byte order) into UTF-8 string.
+ *
+ *	It takes the following arguments:
+ *	in	- input unicode string. It can be null-terminated.
+ *	insize	- size of input string in wide characters.
+ *	out	- result buffer for utf8 string. If out is NULL,
+ *		function returns size of result buffer.
+ *	outsize - size of result buffer.
+ *
+ * RETURN VALUES
+ *	The function returns size of result buffer (in bytes). Zero is returned
+ *	in case of error.
+ *
+ * CAVEATS
+ *	If UCS-4 string contains zero symbols, they will be translated
+ *	as regular symbols.
+ */
+
+        // size_t wchar_to_utf8(const wchar_t *in, size_t insize,
+        //                      char *out, size_t outsize,
+        //                      int flags)
+
+        int flags = 0;
+
+        uint16_t *w, *wlim;
+        wchar_t ch;
+        u_char *p, *lim, *oc;
+        size_t total, n;
+
+        w = input;
+        size_t insize = 0;
+        for (wlim = input; *wlim != 0; wlim++)
+        {
+            insize++;
+        };
+
+        //size_t outsize = insize + (insize >> 1);
+        //u_char *out = malloc( outsize ); // insize *= 1.5
+
+        size_t outsize = buffer_length;
+        u_char *out = (u_char *)buffer;
+
+        p = (u_char *)out;
+        lim = p + outsize;
+        total = 0;
+        for (; w < wlim; w++) {
+            wchar_t W = (wchar_t)*w;
+
+            if (__wchar_forbitten(W) != 0) {
+                if ((flags & UTF8_IGNORE_ERROR) == 0)
+                    return (0);
+                else
+                    continue;
+            }
+
+            if (W == _BOM && (flags & UTF8_SKIP_BOM) != 0)
+                continue;
+
+            if (W < 0) {
+                if ((flags & UTF8_IGNORE_ERROR) == 0)
+                    return (0);
+                continue;
+            } else if (W <= 0x0000007f)
+                n = 1;
+            else if (W <= 0x000007ff)
+                n = 2;
+            else if (W <= 0x0000ffff)
+                n = 3;
+            else if (W <= 0x001fffff)
+                n = 4;
+            else if (W <= 0x03ffffff)
+                n = 5;
+            else /* if (W <= 0x7fffffff) */
+                n = 6;
+
+            total += n;
+
+            if (out == NULL)
+                continue;
+
+            if (lim - p <= n - 1)
+                return (0);		/* no space left */
+
+            /* make it work under different endians */
+            ch = htonl(W);
+            oc = (u_char *)&ch;
+            switch (n) {
+            case 1:
+                *p = oc[3];
+                break;
+
+            case 2:
+                p[1] = _NXT | oc[3] & 0x3f;
+                p[0] = _SEQ2 | (oc[3] >> 6) | ((oc[2] & 0x07) << 2);
+                break;
+
+            case 3:
+                p[2] = _NXT | oc[3] & 0x3f;
+                p[1] = _NXT | (oc[3] >> 6) | ((oc[2] & 0x0f) << 2);
+                p[0] = _SEQ3 | ((oc[2] & 0xf0) >> 4);
+                break;
+
+            case 4:
+                p[3] = _NXT | oc[3] & 0x3f;
+                p[2] = _NXT | (oc[3] >> 6) | ((oc[2] & 0x0f) << 2);
+                p[1] = _NXT | ((oc[2] & 0xf0) >> 4) |
+                    ((oc[1] & 0x03) << 4);
+                p[0] = _SEQ4 | ((oc[1] & 0x1f) >> 2);
+                break;
+
+            case 5:
+                p[4] = _NXT | oc[3] & 0x3f;
+                p[3] = _NXT | (oc[3] >> 6) | ((oc[2] & 0x0f) << 2);
+                p[2] = _NXT | ((oc[2] & 0xf0) >> 4) |
+                    ((oc[1] & 0x03) << 4);
+                p[1] = _NXT | (oc[1] >> 2);
+                p[0] = _SEQ5 | oc[0] & 0x03;
+                break;
+
+            case 6:
+                p[5] = _NXT | oc[3] & 0x3f;
+                p[4] = _NXT | (oc[3] >> 6) | ((oc[2] & 0x0f) << 2);
+                p[3] = _NXT | (oc[2] >> 4) | ((oc[1] & 0x03) << 4);
+                p[2] = _NXT | (oc[1] >> 2);
+                p[1] = _NXT | oc[0] & 0x3f;
+                p[0] = _SEQ6 | ((oc[0] & 0x40) >> 6);
+                break;
+            }
+
+            /*
+             * NOTE: do not check here for forbitten UTF-8 characters.
+             * They cannot appear here because we do proper convertion.
+             */
+
+            p += n;
+        }
 
+        *p = 0;
+        return total;
     }
 }    

coptic.tbl

@@ -1,3 +1,19 @@
+// -*- mode: fundamental; encoding: utf-8; -*_
+//
+// This file is part of libtransliterate
+//
+// Copyright 2012 by Diedrich Vorberg <diedrich@tux4web.de>
+//
+// All Rights Reserved.
+//
+// For more Information on orm see the README and LICENSE file.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+// CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+// INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED.
+
 // These codes follow the TLG Beta Code Quick Reference Guide
 // July 16, 2009
 //