-/* This file is part of
- * ======================================================
+/**
+ * \file encoding.C
+ * This file is part of LyX, the document processor.
+ * Licence details can be found in the file COPYING.
*
- * LyX, The Document Processor
+ * \author Lars Gullik Bjønnes
+ * \author Jean-Marc Lasgouttes
+ * \author Dekel Tsur
*
- * Copyright 1995 Matthias Ettrich
- * Copyright 1995-2001 The LyX Team.
- *
- * ====================================================== */
+ * Full author contact details are available in file CREDITS.
+ */
#include <config.h>
-#ifdef __GNUG__
-#pragma implementation
-#endif
-
#include "encoding.h"
-#include "lyxlex.h"
+
#include "debug.h"
+#include "lyxlex.h"
+#include "lyxrc.h"
#ifndef CXX_GLOBAL_CSTD
using std::strtol;
#endif
using std::endl;
+using std::string;
+
Encodings encodings;
unsigned char arabic_table2[63][4] = {
{0x41, 0x41, 0x41, 0x41}, // 0xc1 = hamza
- {0x42, 0xa1, 0x42, 0x42}, // 0xc2 = ligature madda on alef
- {0x43, 0xa2, 0x43, 0x43}, // 0xc3 = ligature hamza on alef
- {0x44, 0xa3, 0x44, 0x44}, // 0xc4 = ligature hamza on waw
- {0x45, 0xa4, 0x45, 0x45}, // 0xc5 = ligature hamza under alef
- {0xf9, 0xf9, 0xf8, 0xa0}, // 0xc6 = ligature hamza on ya
- {0x47, 0xa5, 0xa5, 0xa5}, // 0xc7 = alef
+ {0x42, 0xa1, 0x42, 0xa1}, // 0xc2 = ligature madda on alef
+ {0x43, 0xa2, 0x43, 0xa2}, // 0xc3 = ligature hamza on alef
+ {0x44, 0xa3, 0x44, 0xa3}, // 0xc4 = ligature hamza on waw
+ {0x45, 0xa4, 0x45, 0xa4}, // 0xc5 = ligature hamza under alef
+ {0x46, 0xf9, 0xf8, 0xa0}, // 0xc6 = ligature hamza on ya
+ {0x47, 0xa5, 0x47, 0xa5}, // 0xc7 = alef
{0x48, 0xae, 0xac, 0xad}, // 0xc8 = baa
- {0x49, 0xb1, 0xaf, 0xb0}, // 0xc9 = taa marbuta
+ {0x49, 0xb1, 0x49, 0xb1}, // 0xc9 = taa marbuta
{0x4a, 0xb4, 0xb2, 0xb3}, // 0xca = taa
{0x4b, 0xb7, 0xb5, 0xb6}, // 0xcb = thaa
{0x4c, 0xba, 0xb8, 0xb9}, // 0xcc = jeem
{0x4d, 0xbd, 0xbb, 0xbc}, // 0xcd = haa
{0x4e, 0xc0, 0xbe, 0xbf}, // 0xce = khaa
- {0x4f, 0xa6, 0xa6, 0xa6}, // 0xcf = dal
+ {0x4f, 0xa6, 0x4f, 0xa6}, // 0xcf = dal
- {0x50, 0xa7, 0xa7, 0xa7}, // 0xd0 = thal
- {0x51, 0xa8, 0xa8, 0xa8}, // 0xd1 = ra
- {0x52, 0xa9, 0xa9, 0xa9}, // 0xd2 = zain
+ {0x50, 0xa7, 0x50, 0xa7}, // 0xd0 = thal
+ {0x51, 0xa8, 0x51, 0xa8}, // 0xd1 = ra
+ {0x52, 0xa9, 0x52, 0xa9}, // 0xd2 = zain
{0x53, 0xc3, 0xc1, 0xc2}, // 0xd3 = seen
{0x54, 0xc6, 0xc4, 0xc5}, // 0xd4 = sheen
{0x55, 0xc9, 0xc7, 0xc8}, // 0xd5 = sad
{0x65, 0xe7, 0xe5, 0xe6}, // 0xe5 = meem
{0x66, 0xea, 0xe8, 0xe9}, // 0xe6 = noon
{0x67, 0xed, 0xeb, 0xec}, // 0xe7 = ha
- {0x68, 0xaa, 0xaa, 0xaa}, // 0xe8 = waw
- {0x69, 0xab, 0xab, 0xab}, // 0xe9 = alef maksura
+ {0x68, 0xaa, 0x68, 0xaa}, // 0xe8 = waw
+ {0x69, 0xab, 0x69, 0xab}, // 0xe9 = alef maksura
{0x6a, 0xf0, 0xee, 0xef}, // 0xea = ya
{0x6b, 0x6b, 0x6b, 0x6b}, // 0xeb = fathatan
{0x6c, 0x6c, 0x6c, 0x6c}, // 0xec = dammatan
} // namespace anon
-bool Encodings::IsComposeChar_hebrew(unsigned char c)
+bool Encodings::isComposeChar_hebrew(unsigned char c)
{
return c <= 0xd2 && c >= 0xc0 &&
c != 0xce && c != 0xd0;
}
-bool Encodings::IsComposeChar_arabic(unsigned char c)
+// Special Arabic letters are ones that do not get connected from left
+// they are hamza, alef_madda, alef_hamza, waw_hamza, alef_hamza_under,
+// alef, tah_marbota, dal, thal, rah, zai, wow, alef_maksoura
+
+bool Encodings::is_arabic_special(unsigned char c)
+{
+ return (c >= 0xc1 && c <= 0xc5) ||
+ c == 0xc7 || c == 0xc9 ||
+ c == 0xcf || c == 0xe8 ||
+ (c >= 0xd0 && c <= 0xd2) ||
+ c == 0xe9;
+}
+
+bool Encodings::isComposeChar_arabic(unsigned char c)
{
return c >= 0xeb && c <= 0xf2;
}
}
-unsigned char Encodings::TransformChar(unsigned char c,
+unsigned char Encodings::transformChar(unsigned char c,
Encodings::Letter_Form form)
{
if (!is_arabic(c))